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: 0.5649
 - Accuracy: 0.9699

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.5653434991836548,
-    "eval_runtime": 13.8185,
-    "eval_samples_per_second": 9.625,
-    "eval_steps_per_second": 0.217,
+    "eval_loss": 0.5649288892745972,
+    "eval_runtime": 1.6014,
+    "eval_samples_per_second": 83.05,
+    "eval_steps_per_second": 1.873,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7544984244832805,
-    "train_runtime": 434.1495,
-    "train_samples_per_second": 7.145,
-    "train_steps_per_second": 0.117
+    "train_loss": 0.7545311299024844,
+    "train_runtime": 73.1643,
+    "train_samples_per_second": 42.398,
+    "train_steps_per_second": 0.697
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.5653434991836548,
-    "eval_runtime": 13.8185,
-    "eval_samples_per_second": 9.625,
-    "eval_steps_per_second": 0.217
+    "eval_loss": 0.5649288892745972,
+    "eval_runtime": 1.6014,
+    "eval_samples_per_second": 83.05,
+    "eval_steps_per_second": 1.873
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7544984244832805,
-    "train_runtime": 434.1495,
-    "train_samples_per_second": 7.145,
-    "train_steps_per_second": 0.117
+    "train_loss": 0.7545311299024844,
+    "train_runtime": 73.1643,
+    "train_samples_per_second": 42.398,
+    "train_steps_per_second": 0.697
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5653434991836548,
+  "best_metric": 0.5649288892745972,
   "best_model_checkpoint": "./beans_outputs/checkpoint-51",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.3434523344039917,
+      "grad_norm": 1.3452003002166748,
       "learning_rate": 1.607843137254902e-05,
       "loss": 0.9886,
       "step": 10
@@ -18,66 +18,66 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.924812030075188,
-      "eval_loss": 0.7759634256362915,
-      "eval_runtime": 14.1609,
-      "eval_samples_per_second": 9.392,
-      "eval_steps_per_second": 0.212,
+      "eval_loss": 0.7764009237289429,
+      "eval_runtime": 1.736,
+      "eval_samples_per_second": 76.612,
+      "eval_steps_per_second": 1.728,
       "step": 17
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 1.200798511505127,
+      "grad_norm": 1.2013428211212158,
       "learning_rate": 1.215686274509804e-05,
-      "loss": 0.8266,
+      "loss": 0.8269,
       "step": 20
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.4084314107894897,
+      "grad_norm": 1.1673593521118164,
       "learning_rate": 8.23529411764706e-06,
-      "loss": 0.7227,
+      "loss": 0.723,
       "step": 30
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9548872180451128,
-      "eval_loss": 0.6200588345527649,
-      "eval_runtime": 13.5575,
-      "eval_samples_per_second": 9.81,
-      "eval_steps_per_second": 0.221,
+      "eval_loss": 0.6197028160095215,
+      "eval_runtime": 1.7224,
+      "eval_samples_per_second": 77.216,
+      "eval_steps_per_second": 1.742,
       "step": 34
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.2539247274398804,
+      "grad_norm": 1.2474788427352905,
       "learning_rate": 4.313725490196079e-06,
       "loss": 0.6427,
       "step": 40
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.133782982826233,
+      "grad_norm": 1.1507647037506104,
       "learning_rate": 3.921568627450981e-07,
-      "loss": 0.6045,
+      "loss": 0.6046,
       "step": 50
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.5653434991836548,
-      "eval_runtime": 15.0207,
-      "eval_samples_per_second": 8.854,
-      "eval_steps_per_second": 0.2,
+      "eval_loss": 0.5649288892745972,
+      "eval_runtime": 1.6272,
+      "eval_samples_per_second": 81.737,
+      "eval_steps_per_second": 1.844,
       "step": 51
     },
     {
       "epoch": 3.0,
       "step": 51,
       "total_flos": 2.4038230623573197e+17,
-      "train_loss": 0.7544984244832805,
-      "train_runtime": 434.1495,
-      "train_samples_per_second": 7.145,
-      "train_steps_per_second": 0.117
+      "train_loss": 0.7545311299024844,
+      "train_runtime": 73.1643,
+      "train_samples_per_second": 42.398,
+      "train_steps_per_second": 0.697
     }
   ],
   "logging_steps": 10,