End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-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: 0.8840
 - Accuracy: 0.8647

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 0.8646616541353384,
-    "eval_loss": 0.8840129971504211,
-    "eval_runtime": 7.9897,
-    "eval_samples_per_second": 16.646,
-    "eval_steps_per_second": 0.375,
+    "eval_loss": 0.8840346336364746,
+    "eval_runtime": 4.7663,
+    "eval_samples_per_second": 27.904,
+    "eval_steps_per_second": 0.629,
     "total_flos": 8.012743541191066e+16,
-    "train_loss": 0.0,
-    "train_runtime": 0.2174,
-    "train_samples_per_second": 4756.041,
-    "train_steps_per_second": 78.194
+    "train_loss": 0.9630123587215648,
+    "train_runtime": 54.0236,
+    "train_samples_per_second": 19.14,
+    "train_steps_per_second": 0.315
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 0.8646616541353384,
-    "eval_loss": 0.8840129971504211,
-    "eval_runtime": 7.9897,
-    "eval_samples_per_second": 16.646,
-    "eval_steps_per_second": 0.375
+    "eval_loss": 0.8840346336364746,
+    "eval_runtime": 4.7663,
+    "eval_samples_per_second": 27.904,
+    "eval_steps_per_second": 0.629
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 8.012743541191066e+16,
-    "train_loss": 0.0,
-    "train_runtime": 0.2174,
-    "train_samples_per_second": 4756.041,
-    "train_steps_per_second": 78.194
+    "train_loss": 0.9630123587215648,
+    "train_runtime": 54.0236,
+    "train_samples_per_second": 19.14,
+    "train_steps_per_second": 0.315
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8840129971504211,
+  "best_metric": 0.8840346336364746,
   "best_model_checkpoint": "./beans_outputs/checkpoint-17",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.3549550771713257,
+      "grad_norm": 1.354477882385254,
       "learning_rate": 8.23529411764706e-06,
       "loss": 0.9983,
       "step": 10
@@ -18,20 +18,20 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.8646616541353384,
-      "eval_loss": 0.8840129971504211,
-      "eval_runtime": 7.6065,
-      "eval_samples_per_second": 17.485,
-      "eval_steps_per_second": 0.394,
+      "eval_loss": 0.8840346336364746,
+      "eval_runtime": 4.3311,
+      "eval_samples_per_second": 30.708,
+      "eval_steps_per_second": 0.693,
       "step": 17
     },
     {
       "epoch": 1.0,
       "step": 17,
       "total_flos": 8.012743541191066e+16,
-      "train_loss": 0.0,
-      "train_runtime": 0.2174,
-      "train_samples_per_second": 4756.041,
-      "train_steps_per_second": 78.194
+      "train_loss": 0.9630123587215648,
+      "train_runtime": 54.0236,
+      "train_samples_per_second": 19.14,
+      "train_steps_per_second": 0.315
     }
   ],
   "logging_steps": 10,