Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 65.767,
     "eval_steps_per_second": 2.349,
     "total_flos": 2.071360882398044e+17,
-    "train_loss": 0.5642238571530297,
-    "train_runtime": 242.7921,
-    "train_samples_per_second": 11.009,
-    "train_steps_per_second": 0.086
+    "train_loss": 0.5111370115053087,
+    "train_runtime": 228.9442,
+    "train_samples_per_second": 11.675,
+    "train_steps_per_second": 0.092
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26a23d997b8165baea51a13246c69af462e27a0c5ff581cebee6f018c21b3c1
+oid sha256:03553b005cca996a8f3f9348ec2d19b5814dc0106f855e29bfd7f06c01a530f3
 size 343268717

runs/Jul20_22-51-27_fcbe542fc008/events.out.tfevents.1689894625.fcbe542fc008.53766.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d2bdaab907dff1ddc317331f386036bf16f8c6f1854e562108f04a733bd078
+size 4472

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.071360882398044e+17,
-    "train_loss": 0.5642238571530297,
-    "train_runtime": 242.7921,
-    "train_samples_per_second": 11.009,
-    "train_steps_per_second": 0.086
+    "train_loss": 0.5111370115053087,
+    "train_runtime": 228.9442,
+    "train_samples_per_second": 11.675,
+    "train_steps_per_second": 0.092
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6995515695067265,
-  "best_model_checkpoint": "vit-base-patch16-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.8295964125560538,
+  "best_model_checkpoint": "vit-base-patch16-224-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": 0.695067264573991,
-      "eval_loss": 0.5611284971237183,
-      "eval_runtime": 3.5824,
-      "eval_samples_per_second": 62.248,
-      "eval_steps_per_second": 1.954,
+      "eval_accuracy": 0.8295964125560538,
+      "eval_loss": 0.49411410093307495,
+      "eval_runtime": 3.3119,
+      "eval_samples_per_second": 67.333,
+      "eval_steps_per_second": 2.114,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5947,
+      "loss": 0.5365,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6995515695067265,
-      "eval_loss": 0.5539332032203674,
-      "eval_runtime": 3.3759,
-      "eval_samples_per_second": 66.056,
-      "eval_steps_per_second": 2.073,
+      "eval_accuracy": 0.8071748878923767,
+      "eval_loss": 0.5048662424087524,
+      "eval_runtime": 3.5367,
+      "eval_samples_per_second": 63.054,
+      "eval_steps_per_second": 1.979,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5369,
+      "loss": 0.4893,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.672645739910314,
-      "eval_loss": 0.5587254762649536,
-      "eval_runtime": 3.5944,
-      "eval_samples_per_second": 62.041,
-      "eval_steps_per_second": 1.947,
+      "eval_accuracy": 0.7982062780269058,
+      "eval_loss": 0.5039920806884766,
+      "eval_runtime": 3.3683,
+      "eval_samples_per_second": 66.205,
+      "eval_steps_per_second": 2.078,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 2.071360882398044e+17,
-      "train_loss": 0.5642238571530297,
-      "train_runtime": 242.7921,
-      "train_samples_per_second": 11.009,
-      "train_steps_per_second": 0.086
+      "train_loss": 0.5111370115053087,
+      "train_runtime": 228.9442,
+      "train_samples_per_second": 11.675,
+      "train_steps_per_second": 0.092
     }
   ],
   "max_steps": 21,