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: 0.5650
 - Accuracy: 0.9699

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.564608097076416,
-    "eval_runtime": 17.4903,
-    "eval_samples_per_second": 7.604,
-    "eval_steps_per_second": 0.172,
+    "eval_loss": 0.5649893879890442,
+    "eval_runtime": 10.3591,
+    "eval_samples_per_second": 12.839,
+    "eval_steps_per_second": 0.29,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7542588278359058,
-    "train_runtime": 427.2792,
-    "train_samples_per_second": 7.26,
-    "train_steps_per_second": 0.119
+    "train_loss": 0.7544311717444775,
+    "train_runtime": 303.929,
+    "train_samples_per_second": 10.206,
+    "train_steps_per_second": 0.168
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.564608097076416,
-    "eval_runtime": 17.4903,
-    "eval_samples_per_second": 7.604,
-    "eval_steps_per_second": 0.172
+    "eval_loss": 0.5649893879890442,
+    "eval_runtime": 10.3591,
+    "eval_samples_per_second": 12.839,
+    "eval_steps_per_second": 0.29
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7542588278359058,
-    "train_runtime": 427.2792,
-    "train_samples_per_second": 7.26,
-    "train_steps_per_second": 0.119
+    "train_loss": 0.7544311717444775,
+    "train_runtime": 303.929,
+    "train_samples_per_second": 10.206,
+    "train_steps_per_second": 0.168
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.564608097076416,
+  "best_metric": 0.5649893879890442,
   "best_model_checkpoint": "./beans_outputs/checkpoint-51",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.342671275138855,
+      "grad_norm": 1.344062328338623,
       "learning_rate": 1.607843137254902e-05,
       "loss": 0.9886,
       "step": 10
@@ -18,66 +18,66 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.924812030075188,
-      "eval_loss": 0.7758036851882935,
-      "eval_runtime": 13.3932,
-      "eval_samples_per_second": 9.93,
-      "eval_steps_per_second": 0.224,
+      "eval_loss": 0.775945246219635,
+      "eval_runtime": 10.3217,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 0.291,
       "step": 17
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 1.2002716064453125,
+      "grad_norm": 1.2051916122436523,
       "learning_rate": 1.215686274509804e-05,
-      "loss": 0.8266,
+      "loss": 0.8267,
       "step": 20
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.1757010221481323,
+      "grad_norm": 1.185186743736267,
       "learning_rate": 8.23529411764706e-06,
-      "loss": 0.7226,
+      "loss": 0.7228,
       "step": 30
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9548872180451128,
-      "eval_loss": 0.6197953820228577,
-      "eval_runtime": 12.3405,
-      "eval_samples_per_second": 10.778,
-      "eval_steps_per_second": 0.243,
+      "eval_loss": 0.6195416450500488,
+      "eval_runtime": 11.1093,
+      "eval_samples_per_second": 11.972,
+      "eval_steps_per_second": 0.27,
       "step": 34
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.2492908239364624,
+      "grad_norm": 1.2483948469161987,
       "learning_rate": 4.313725490196079e-06,
-      "loss": 0.6423,
+      "loss": 0.6425,
       "step": 40
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.134194254875183,
+      "grad_norm": 1.1406564712524414,
       "learning_rate": 3.921568627450981e-07,
-      "loss": 0.6041,
+      "loss": 0.6046,
       "step": 50
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.564608097076416,
-      "eval_runtime": 12.5805,
-      "eval_samples_per_second": 10.572,
-      "eval_steps_per_second": 0.238,
+      "eval_loss": 0.5649893879890442,
+      "eval_runtime": 11.5086,
+      "eval_samples_per_second": 11.557,
+      "eval_steps_per_second": 0.261,
       "step": 51
     },
     {
       "epoch": 3.0,
       "step": 51,
       "total_flos": 2.4038230623573197e+17,
-      "train_loss": 0.7542588278359058,
-      "train_runtime": 427.2792,
-      "train_samples_per_second": 7.26,
-      "train_steps_per_second": 0.119
+      "train_loss": 0.7544311717444775,
+      "train_runtime": 303.929,
+      "train_samples_per_second": 10.206,
+      "train_steps_per_second": 0.168
     }
   ],
   "logging_steps": 10,