🍻 cheers

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 model-index:
 - name: ryan_model314_3
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ryan_model314_3
 
-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 None 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: 0.2745
 - Na Accuracy: 0.96

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 2.0,
-    "eval_loss": 0.2696247398853302,
+    "eval_loss": 0.2744598984718323,
     "eval_na_accuracy": 0.96,
-    "eval_ordinal_accuracy": 0.5,
-    "eval_ordinal_mae": 1.168388410445914,
-    "eval_runtime": 4.4189,
-    "eval_samples_per_second": 22.63,
-    "eval_steps_per_second": 2.942,
-    "train_loss": 0.3214722058129689,
-    "train_runtime": 262.7567,
-    "train_samples_per_second": 7.612,
-    "train_steps_per_second": 0.48
+    "eval_ordinal_accuracy": 0.5108695652173914,
+    "eval_ordinal_mae": 0.5806456123182611,
+    "eval_runtime": 4.777,
+    "eval_samples_per_second": 20.934,
+    "eval_steps_per_second": 2.721,
+    "train_loss": 0.32528334193759495,
+    "train_runtime": 229.1686,
+    "train_samples_per_second": 8.727,
+    "train_steps_per_second": 0.55
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.0,
-    "eval_loss": 0.2696247398853302,
+    "eval_loss": 0.2744598984718323,
     "eval_na_accuracy": 0.96,
-    "eval_ordinal_accuracy": 0.5,
-    "eval_ordinal_mae": 1.168388410445914,
-    "eval_runtime": 4.4189,
-    "eval_samples_per_second": 22.63,
-    "eval_steps_per_second": 2.942
+    "eval_ordinal_accuracy": 0.5108695652173914,
+    "eval_ordinal_mae": 0.5806456123182611,
+    "eval_runtime": 4.777,
+    "eval_samples_per_second": 20.934,
+    "eval_steps_per_second": 2.721
 }

runs/Mar27_07-58-37_ryanserver/events.out.tfevents.1711541026.ryanserver.7494.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e09d16c9bfb0e2ff0ead4d0b9200d9fbf2836f3425cf553d96e60269c83ef38
+size 521

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
-    "train_loss": 0.3214722058129689,
-    "train_runtime": 262.7567,
-    "train_samples_per_second": 7.612,
-    "train_steps_per_second": 0.48
+    "train_loss": 0.32528334193759495,
+    "train_runtime": 229.1686,
+    "train_samples_per_second": 8.727,
+    "train_steps_per_second": 0.55
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.2696247398853302,
+  "best_metric": 0.2744598984718323,
   "best_model_checkpoint": "./ryan_model314_3/checkpoint-100",
   "epoch": 2.0,
   "eval_steps": 50,
@@ -10,48 +10,48 @@
   "log_history": [
     {
       "epoch": 0.79,
-      "grad_norm": 0.766051709651947,
+      "grad_norm": 0.808198094367981,
       "learning_rate": 0.00012063492063492063,
-      "loss": 0.4088,
+      "loss": 0.4094,
       "step": 50
     },
     {
       "epoch": 0.79,
-      "eval_loss": 0.30989590287208557,
-      "eval_na_accuracy": 0.93,
-      "eval_ordinal_accuracy": 0.43478260869565216,
-      "eval_ordinal_mae": 1.1052913616381967,
-      "eval_runtime": 14.2973,
-      "eval_samples_per_second": 6.994,
-      "eval_steps_per_second": 0.909,
+      "eval_loss": 0.31280139088630676,
+      "eval_na_accuracy": 0.94,
+      "eval_ordinal_accuracy": 0.40217391304347827,
+      "eval_ordinal_mae": 0.6332903986837229,
+      "eval_runtime": 11.6495,
+      "eval_samples_per_second": 8.584,
+      "eval_steps_per_second": 1.116,
       "step": 50
     },
     {
       "epoch": 1.59,
-      "grad_norm": 0.8156992793083191,
+      "grad_norm": 0.8316417336463928,
       "learning_rate": 4.126984126984127e-05,
-      "loss": 0.2813,
+      "loss": 0.29,
       "step": 100
     },
     {
       "epoch": 1.59,
-      "eval_loss": 0.2696247398853302,
+      "eval_loss": 0.2744598984718323,
       "eval_na_accuracy": 0.96,
-      "eval_ordinal_accuracy": 0.5,
-      "eval_ordinal_mae": 1.168388410445914,
-      "eval_runtime": 4.0273,
-      "eval_samples_per_second": 24.831,
-      "eval_steps_per_second": 3.228,
+      "eval_ordinal_accuracy": 0.5108695652173914,
+      "eval_ordinal_mae": 0.5806456123182611,
+      "eval_runtime": 4.1502,
+      "eval_samples_per_second": 24.095,
+      "eval_steps_per_second": 3.132,
       "step": 100
     },
     {
       "epoch": 2.0,
       "step": 126,
       "total_flos": 1.5498953551872e+17,
-      "train_loss": 0.3214722058129689,
-      "train_runtime": 262.7567,
-      "train_samples_per_second": 7.612,
-      "train_steps_per_second": 0.48
+      "train_loss": 0.32528334193759495,
+      "train_runtime": 229.1686,
+      "train_samples_per_second": 8.727,
+      "train_steps_per_second": 0.55
     }
   ],
   "logging_steps": 50,