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": 0.6014416331336612,
-    "train_runtime": 84.9872,
-    "train_samples_per_second": 31.452,
-    "train_steps_per_second": 0.247
+    "train_loss": 0.5598951095626468,
+    "train_runtime": 85.4744,
+    "train_samples_per_second": 31.273,
+    "train_steps_per_second": 0.246
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae32a044e988c4a8845b64f2fef15a8e32b74cc1b9eb2ebf4acd6379764dab7
+oid sha256:eaf2e7e8a3f7d4d6fd131f96bf10950d3019653cf76871136ece505094236ed3
 size 110394865

runs/Jul20_19-45-58_fcbe542fc008/events.out.tfevents.1689884669.fcbe542fc008.344.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b550fa7041272142a9cf1efa17c71f60ee2a79e7b0f985594127084184abe0
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6014416331336612,
-    "train_runtime": 84.9872,
-    "train_samples_per_second": 31.452,
-    "train_steps_per_second": 0.247
+    "train_loss": 0.5598951095626468,
+    "train_runtime": 85.4744,
+    "train_samples_per_second": 31.273,
+    "train_steps_per_second": 0.246
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7040358744394619,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
+  "best_metric": 0.7847533632286996,
+  "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": 0.6995515695067265,
-      "eval_loss": 0.5877744555473328,
-      "eval_runtime": 1.5299,
-      "eval_samples_per_second": 145.765,
-      "eval_steps_per_second": 4.576,
+      "eval_accuracy": 0.7847533632286996,
+      "eval_loss": 0.5494154691696167,
+      "eval_runtime": 1.5729,
+      "eval_samples_per_second": 141.78,
+      "eval_steps_per_second": 4.45,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6236,
+      "loss": 0.5689,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6816143497757847,
-      "eval_loss": 0.5972143411636353,
-      "eval_runtime": 1.4974,
-      "eval_samples_per_second": 148.929,
-      "eval_steps_per_second": 4.675,
+      "eval_accuracy": 0.7399103139013453,
+      "eval_loss": 0.5553792715072632,
+      "eval_runtime": 1.5212,
+      "eval_samples_per_second": 146.598,
+      "eval_steps_per_second": 4.602,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5818,
+      "loss": 0.5487,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7040358744394619,
-      "eval_loss": 0.5894758105278015,
-      "eval_runtime": 1.4987,
-      "eval_samples_per_second": 148.794,
-      "eval_steps_per_second": 4.671,
+      "eval_accuracy": 0.7399103139013453,
+      "eval_loss": 0.566148579120636,
+      "eval_runtime": 1.5156,
+      "eval_samples_per_second": 147.139,
+      "eval_steps_per_second": 4.619,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6014416331336612,
-      "train_runtime": 84.9872,
-      "train_samples_per_second": 31.452,
-      "train_steps_per_second": 0.247
+      "train_loss": 0.5598951095626468,
+      "train_runtime": 85.4744,
+      "train_samples_per_second": 31.273,
+      "train_steps_per_second": 0.246
     }
   ],
   "max_steps": 21,