cheers again

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans-tutorial
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2125
+- Loss: 0.2011
 - Accuracy: 0.9850
 
 ## Model description

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
-    "eval_loss": 0.16576917469501495,
-    "eval_runtime": 2.0958,
-    "eval_samples_per_second": 63.46,
-    "eval_steps_per_second": 8.111,
+    "eval_loss": 0.20106938481330872,
+    "eval_runtime": 2.1271,
+    "eval_samples_per_second": 62.526,
+    "eval_steps_per_second": 7.992,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 3.2931016008100974e-06,
-    "train_runtime": 143.2513,
-    "train_samples_per_second": 36.09,
-    "train_steps_per_second": 2.269
+    "train_loss": 2.037791106291619e-07,
+    "train_runtime": 179.5207,
+    "train_samples_per_second": 28.799,
+    "train_steps_per_second": 1.81
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
-    "eval_loss": 0.16576917469501495,
-    "eval_runtime": 2.0958,
-    "eval_samples_per_second": 63.46,
-    "eval_steps_per_second": 8.111
+    "eval_loss": 0.20106938481330872,
+    "eval_runtime": 2.1271,
+    "eval_samples_per_second": 62.526,
+    "eval_steps_per_second": 7.992
 }

runs/Jan24_02-46-57_579caf070ae1/events.out.tfevents.1706064629.579caf070ae1.3225.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99bb43fbeb1551edf505c3871b886578a3edc4a29d8461f2c43fb08aca939135
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 3.2931016008100974e-06,
-    "train_runtime": 143.2513,
-    "train_samples_per_second": 36.09,
-    "train_steps_per_second": 2.269
+    "train_loss": 2.037791106291619e-07,
+    "train_runtime": 179.5207,
+    "train_samples_per_second": 28.799,
+    "train_steps_per_second": 1.81
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.16576917469501495,
+  "best_metric": 0.20106938481330872,
   "best_model_checkpoint": "./vit-base-beans-tutorial/checkpoint-100",
   "epoch": 5.0,
   "eval_steps": 100,
@@ -71,10 +71,10 @@
     {
       "epoch": 1.54,
       "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.16576917469501495,
-      "eval_runtime": 2.163,
-      "eval_samples_per_second": 61.49,
-      "eval_steps_per_second": 7.86,
+      "eval_loss": 0.20106938481330872,
+      "eval_runtime": 1.8204,
+      "eval_samples_per_second": 73.06,
+      "eval_steps_per_second": 9.339,
       "step": 100
     },
     {
@@ -140,10 +140,10 @@
     {
       "epoch": 3.08,
       "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.17416749894618988,
-      "eval_runtime": 1.7693,
-      "eval_samples_per_second": 75.171,
-      "eval_steps_per_second": 9.608,
+      "eval_loss": 0.20929287374019623,
+      "eval_runtime": 3.698,
+      "eval_samples_per_second": 35.966,
+      "eval_steps_per_second": 4.597,
       "step": 200
     },
     {
@@ -209,10 +209,10 @@
     {
       "epoch": 4.62,
       "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.17769162356853485,
-      "eval_runtime": 1.7753,
-      "eval_samples_per_second": 74.918,
-      "eval_steps_per_second": 9.576,
+      "eval_loss": 0.21252359449863434,
+      "eval_runtime": 1.8184,
+      "eval_samples_per_second": 73.139,
+      "eval_steps_per_second": 9.349,
       "step": 300
     },
     {
@@ -231,10 +231,10 @@
       "epoch": 5.0,
       "step": 325,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 3.2931016008100974e-06,
-      "train_runtime": 143.2513,
-      "train_samples_per_second": 36.09,
-      "train_steps_per_second": 2.269
+      "train_loss": 2.037791106291619e-07,
+      "train_runtime": 179.5207,
+      "train_samples_per_second": 28.799,
+      "train_steps_per_second": 1.81
     }
   ],
   "logging_steps": 10,