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: 0.5671
 - Accuracy: 0.9699

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.564985454082489,
-    "eval_runtime": 7.5272,
-    "eval_samples_per_second": 17.669,
-    "eval_steps_per_second": 0.399,
+    "eval_loss": 0.5670764446258545,
+    "eval_runtime": 9.4799,
+    "eval_samples_per_second": 14.03,
+    "eval_steps_per_second": 0.316,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7543852925300598,
-    "train_runtime": 244.2648,
-    "train_samples_per_second": 12.699,
-    "train_steps_per_second": 0.209
+    "train_loss": 0.7555306378532859,
+    "train_runtime": 266.789,
+    "train_samples_per_second": 11.627,
+    "train_steps_per_second": 0.191
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.564985454082489,
-    "eval_runtime": 7.5272,
-    "eval_samples_per_second": 17.669,
-    "eval_steps_per_second": 0.399
+    "eval_loss": 0.5670764446258545,
+    "eval_runtime": 9.4799,
+    "eval_samples_per_second": 14.03,
+    "eval_steps_per_second": 0.316
 }

runs/Jul07_15-18-55_ring19/events.out.tfevents.1720380221.ring19.183051.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21eb185a9c5bb7dd456c81cb0c31a0b01656c63b7aa34db5d341006f78c1cae8
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7543852925300598,
-    "train_runtime": 244.2648,
-    "train_samples_per_second": 12.699,
-    "train_steps_per_second": 0.209
+    "train_loss": 0.7555306378532859,
+    "train_runtime": 266.789,
+    "train_samples_per_second": 11.627,
+    "train_steps_per_second": 0.191
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.564985454082489,
+  "best_metric": 0.5670764446258545,
   "best_model_checkpoint": "./beans_outputs/checkpoint-51",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.3447999954223633,
+      "grad_norm": 1.3424246311187744,
       "learning_rate": 1.607843137254902e-05,
       "loss": 0.9886,
       "step": 10
@@ -18,66 +18,66 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.924812030075188,
-      "eval_loss": 0.7760571837425232,
-      "eval_runtime": 6.9374,
-      "eval_samples_per_second": 19.171,
-      "eval_steps_per_second": 0.432,
+      "eval_loss": 0.7763344645500183,
+      "eval_runtime": 8.9578,
+      "eval_samples_per_second": 14.847,
+      "eval_steps_per_second": 0.335,
       "step": 17
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 1.1939303874969482,
+      "grad_norm": 1.1987462043762207,
       "learning_rate": 1.215686274509804e-05,
-      "loss": 0.8267,
+      "loss": 0.8268,
       "step": 20
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.2060675621032715,
+      "grad_norm": 1.1679188013076782,
       "learning_rate": 8.23529411764706e-06,
-      "loss": 0.7227,
+      "loss": 0.7243,
       "step": 30
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9548872180451128,
-      "eval_loss": 0.6196414232254028,
-      "eval_runtime": 6.8532,
-      "eval_samples_per_second": 19.407,
-      "eval_steps_per_second": 0.438,
+      "eval_loss": 0.6225273013114929,
+      "eval_runtime": 8.7315,
+      "eval_samples_per_second": 15.232,
+      "eval_steps_per_second": 0.344,
       "step": 34
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.242749810218811,
+      "grad_norm": 1.24931001663208,
       "learning_rate": 4.313725490196079e-06,
-      "loss": 0.6424,
+      "loss": 0.6446,
       "step": 40
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.1439201831817627,
+      "grad_norm": 1.1497653722763062,
       "learning_rate": 3.921568627450981e-07,
-      "loss": 0.6044,
+      "loss": 0.6062,
       "step": 50
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.564985454082489,
-      "eval_runtime": 7.9686,
-      "eval_samples_per_second": 16.691,
-      "eval_steps_per_second": 0.376,
+      "eval_loss": 0.5670764446258545,
+      "eval_runtime": 9.9384,
+      "eval_samples_per_second": 13.382,
+      "eval_steps_per_second": 0.302,
       "step": 51
     },
     {
       "epoch": 3.0,
       "step": 51,
       "total_flos": 2.4038230623573197e+17,
-      "train_loss": 0.7543852925300598,
-      "train_runtime": 244.2648,
-      "train_samples_per_second": 12.699,
-      "train_steps_per_second": 0.209
+      "train_loss": 0.7555306378532859,
+      "train_runtime": 266.789,
+      "train_samples_per_second": 11.627,
+      "train_steps_per_second": 0.191
     }
   ],
   "logging_steps": 10,