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": 0.5111370115053087,
-    "train_runtime": 228.9442,
-    "train_samples_per_second": 11.675,
+    "train_loss": 0.4825253642740704,
+    "train_runtime": 229.1314,
+    "train_samples_per_second": 11.666,
     "train_steps_per_second": 0.092
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03553b005cca996a8f3f9348ec2d19b5814dc0106f855e29bfd7f06c01a530f3
+oid sha256:62c68f37de60bcefa944118b191f9322a48824432535af32c60a20060d52f3ec
 size 343268717

runs/Jul20_22-51-27_fcbe542fc008/events.out.tfevents.1689894893.fcbe542fc008.53766.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0c9fb61ea6c4cee97b2cd6751b533fdaa485024a416fa62bad5ab539b0814c
+size 4472

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.071360882398044e+17,
-    "train_loss": 0.5111370115053087,
-    "train_runtime": 228.9442,
-    "train_samples_per_second": 11.675,
+    "train_loss": 0.4825253642740704,
+    "train_runtime": 229.1314,
+    "train_samples_per_second": 11.666,
     "train_steps_per_second": 0.092
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8295964125560538,
+  "best_metric": 0.8430493273542601,
   "best_model_checkpoint": "vit-base-patch16-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
@@ -9,50 +9,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8295964125560538,
-      "eval_loss": 0.49411410093307495,
-      "eval_runtime": 3.3119,
-      "eval_samples_per_second": 67.333,
-      "eval_steps_per_second": 2.114,
+      "eval_accuracy": 0.8430493273542601,
+      "eval_loss": 0.4596026539802551,
+      "eval_runtime": 3.3311,
+      "eval_samples_per_second": 66.944,
+      "eval_steps_per_second": 2.101,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5365,
+      "loss": 0.5115,
       "step": 10
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.8071748878923767,
-      "eval_loss": 0.5048662424087524,
-      "eval_runtime": 3.5367,
-      "eval_samples_per_second": 63.054,
-      "eval_steps_per_second": 1.979,
+      "eval_loss": 0.4634478688240051,
+      "eval_runtime": 3.3321,
+      "eval_samples_per_second": 66.924,
+      "eval_steps_per_second": 2.101,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.4893,
+      "loss": 0.4571,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7982062780269058,
-      "eval_loss": 0.5039920806884766,
-      "eval_runtime": 3.3683,
-      "eval_samples_per_second": 66.205,
-      "eval_steps_per_second": 2.078,
+      "eval_accuracy": 0.8251121076233184,
+      "eval_loss": 0.4669438898563385,
+      "eval_runtime": 3.496,
+      "eval_samples_per_second": 63.788,
+      "eval_steps_per_second": 2.002,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 2.071360882398044e+17,
-      "train_loss": 0.5111370115053087,
-      "train_runtime": 228.9442,
-      "train_samples_per_second": 11.675,
+      "train_loss": 0.4825253642740704,
+      "train_runtime": 229.1314,
+      "train_samples_per_second": 11.666,
       "train_steps_per_second": 0.092
     }
   ],