Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 131.885,
     "eval_steps_per_second": 4.71,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6091077100662958,
-    "train_runtime": 83.2263,
-    "train_samples_per_second": 32.117,
-    "train_steps_per_second": 0.252
+    "train_loss": 0.6014416331336612,
+    "train_runtime": 84.9872,
+    "train_samples_per_second": 31.452,
+    "train_steps_per_second": 0.247
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194f8d6a477d4beea58563b35deef7219f7458a409a84ff55b399089ca6a0e41
+oid sha256:fae32a044e988c4a8845b64f2fef15a8e32b74cc1b9eb2ebf4acd6379764dab7
 size 110394865

runs/Jul20_19-45-58_fcbe542fc008/events.out.tfevents.1689884561.fcbe542fc008.344.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2ab23129bac4ed42b843d0ff81a7e723003e3db46ef6a406644e20a00cc479
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6091077100662958,
-    "train_runtime": 83.2263,
-    "train_samples_per_second": 32.117,
-    "train_steps_per_second": 0.252
+    "train_loss": 0.6014416331336612,
+    "train_runtime": 84.9872,
+    "train_samples_per_second": 31.452,
+    "train_steps_per_second": 0.247
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6412556053811659,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.7040358744394619,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6412556053811659,
-      "eval_loss": 0.6205761432647705,
-      "eval_runtime": 1.7726,
-      "eval_samples_per_second": 125.804,
-      "eval_steps_per_second": 3.949,
+      "eval_accuracy": 0.6995515695067265,
+      "eval_loss": 0.5877744555473328,
+      "eval_runtime": 1.5299,
+      "eval_samples_per_second": 145.765,
+      "eval_steps_per_second": 4.576,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6223,
+      "loss": 0.6236,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6367713004484304,
-      "eval_loss": 0.6116213202476501,
-      "eval_runtime": 1.4981,
-      "eval_samples_per_second": 148.851,
-      "eval_steps_per_second": 4.672,
+      "eval_accuracy": 0.6816143497757847,
+      "eval_loss": 0.5972143411636353,
+      "eval_runtime": 1.4974,
+      "eval_samples_per_second": 148.929,
+      "eval_steps_per_second": 4.675,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5982,
+      "loss": 0.5818,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6412556053811659,
-      "eval_loss": 0.6154299974441528,
-      "eval_runtime": 1.5114,
-      "eval_samples_per_second": 147.545,
-      "eval_steps_per_second": 4.631,
+      "eval_accuracy": 0.7040358744394619,
+      "eval_loss": 0.5894758105278015,
+      "eval_runtime": 1.4987,
+      "eval_samples_per_second": 148.794,
+      "eval_steps_per_second": 4.671,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6091077100662958,
-      "train_runtime": 83.2263,
-      "train_samples_per_second": 32.117,
-      "train_steps_per_second": 0.252
+      "train_loss": 0.6014416331336612,
+      "train_runtime": 84.9872,
+      "train_samples_per_second": 31.452,
+      "train_steps_per_second": 0.247
     }
   ],
   "max_steps": 21,