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: 0.5642
 - Accuracy: 0.9699

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.5670764446258545,
-    "eval_runtime": 9.4799,
-    "eval_samples_per_second": 14.03,
-    "eval_steps_per_second": 0.316,
+    "eval_loss": 0.5641857385635376,
+    "eval_runtime": 8.3136,
+    "eval_samples_per_second": 15.998,
+    "eval_steps_per_second": 0.361,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7555306378532859,
-    "train_runtime": 266.789,
-    "train_samples_per_second": 11.627,
-    "train_steps_per_second": 0.191
+    "train_loss": 0.7540177586031895,
+    "train_runtime": 260.6448,
+    "train_samples_per_second": 11.901,
+    "train_steps_per_second": 0.196
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.5670764446258545,
-    "eval_runtime": 9.4799,
-    "eval_samples_per_second": 14.03,
-    "eval_steps_per_second": 0.316
+    "eval_loss": 0.5641857385635376,
+    "eval_runtime": 8.3136,
+    "eval_samples_per_second": 15.998,
+    "eval_steps_per_second": 0.361
 }

runs/Jul07_15-30-08_ring19/events.out.tfevents.1720380887.ring19.193500.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c168e3c99bbeb4ec348c985aae60b4f1b5ff78865007dfda2da66762892b04
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7555306378532859,
-    "train_runtime": 266.789,
-    "train_samples_per_second": 11.627,
-    "train_steps_per_second": 0.191
+    "train_loss": 0.7540177586031895,
+    "train_runtime": 260.6448,
+    "train_samples_per_second": 11.901,
+    "train_steps_per_second": 0.196
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5670764446258545,
+  "best_metric": 0.5641857385635376,
   "best_model_checkpoint": "./beans_outputs/checkpoint-51",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.3424246311187744,
+      "grad_norm": 1.3421605825424194,
       "learning_rate": 1.607843137254902e-05,
       "loss": 0.9886,
       "step": 10
@@ -18,66 +18,66 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.924812030075188,
-      "eval_loss": 0.7763344645500183,
-      "eval_runtime": 8.9578,
-      "eval_samples_per_second": 14.847,
-      "eval_steps_per_second": 0.335,
+      "eval_loss": 0.7757352590560913,
+      "eval_runtime": 8.5619,
+      "eval_samples_per_second": 15.534,
+      "eval_steps_per_second": 0.35,
       "step": 17
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 1.1987462043762207,
+      "grad_norm": 1.1954083442687988,
       "learning_rate": 1.215686274509804e-05,
-      "loss": 0.8268,
+      "loss": 0.8266,
       "step": 20
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.1679188013076782,
+      "grad_norm": 1.1710609197616577,
       "learning_rate": 8.23529411764706e-06,
-      "loss": 0.7243,
+      "loss": 0.7223,
       "step": 30
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9548872180451128,
-      "eval_loss": 0.6225273013114929,
-      "eval_runtime": 8.7315,
-      "eval_samples_per_second": 15.232,
-      "eval_steps_per_second": 0.344,
+      "eval_loss": 0.6193692088127136,
+      "eval_runtime": 9.1501,
+      "eval_samples_per_second": 14.535,
+      "eval_steps_per_second": 0.328,
       "step": 34
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.24931001663208,
+      "grad_norm": 1.2411857843399048,
       "learning_rate": 4.313725490196079e-06,
-      "loss": 0.6446,
+      "loss": 0.6419,
       "step": 40
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.1497653722763062,
+      "grad_norm": 1.1404906511306763,
       "learning_rate": 3.921568627450981e-07,
-      "loss": 0.6062,
+      "loss": 0.6036,
       "step": 50
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.5670764446258545,
-      "eval_runtime": 9.9384,
-      "eval_samples_per_second": 13.382,
-      "eval_steps_per_second": 0.302,
+      "eval_loss": 0.5641857385635376,
+      "eval_runtime": 9.221,
+      "eval_samples_per_second": 14.424,
+      "eval_steps_per_second": 0.325,
       "step": 51
     },
     {
       "epoch": 3.0,
       "step": 51,
       "total_flos": 2.4038230623573197e+17,
-      "train_loss": 0.7555306378532859,
-      "train_runtime": 266.789,
-      "train_samples_per_second": 11.627,
-      "train_steps_per_second": 0.191
+      "train_loss": 0.7540177586031895,
+      "train_runtime": 260.6448,
+      "train_samples_per_second": 11.901,
+      "train_steps_per_second": 0.196
     }
   ],
   "logging_steps": 10,