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: 0.3442
 - Accuracy: 0.9624

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.3435966670513153,
-    "eval_runtime": 1.4914,
-    "eval_samples_per_second": 89.176,
-    "eval_steps_per_second": 2.011,
+    "eval_accuracy": 0.9624060150375939,
+    "eval_loss": 0.34422725439071655,
+    "eval_runtime": 8.5078,
+    "eval_samples_per_second": 15.633,
+    "eval_steps_per_second": 0.353,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 0.5855801442090203,
-    "train_runtime": 115.6504,
-    "train_samples_per_second": 44.704,
-    "train_steps_per_second": 0.735
+    "train_loss": 0.5861698781742769,
+    "train_runtime": 731.5711,
+    "train_samples_per_second": 7.067,
+    "train_steps_per_second": 0.116
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9699248120300752,
-    "eval_loss": 0.3435966670513153,
-    "eval_runtime": 1.4914,
-    "eval_samples_per_second": 89.176,
-    "eval_steps_per_second": 2.011
+    "eval_accuracy": 0.9624060150375939,
+    "eval_loss": 0.34422725439071655,
+    "eval_runtime": 8.5078,
+    "eval_samples_per_second": 15.633,
+    "eval_steps_per_second": 0.353
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 0.5855801442090203,
-    "train_runtime": 115.6504,
-    "train_samples_per_second": 44.704,
-    "train_steps_per_second": 0.735
+    "train_loss": 0.5861698781742769,
+    "train_runtime": 731.5711,
+    "train_samples_per_second": 7.067,
+    "train_steps_per_second": 0.116
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.3435966670513153,
+  "best_metric": 0.34422725439071655,
   "best_model_checkpoint": "./beans_outputs/checkpoint-85",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.3392215967178345,
+      "grad_norm": 1.339193344116211,
       "learning_rate": 1.7647058823529414e-05,
       "loss": 0.9867,
       "step": 10
@@ -18,105 +18,105 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.924812030075188,
-      "eval_loss": 0.7570837736129761,
-      "eval_runtime": 1.7216,
-      "eval_samples_per_second": 77.256,
-      "eval_steps_per_second": 1.743,
+      "eval_loss": 0.7571204304695129,
+      "eval_runtime": 17.907,
+      "eval_samples_per_second": 7.427,
+      "eval_steps_per_second": 0.168,
       "step": 17
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 1.1864875555038452,
+      "grad_norm": 1.186477780342102,
       "learning_rate": 1.5294117647058822e-05,
-      "loss": 0.8133,
+      "loss": 0.8134,
       "step": 20
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.1501308679580688,
+      "grad_norm": 1.7653396129608154,
       "learning_rate": 1.2941176470588238e-05,
-      "loss": 0.69,
+      "loss": 0.6897,
       "step": 30
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.9624060150375939,
-      "eval_loss": 0.5540627837181091,
-      "eval_runtime": 1.6836,
-      "eval_samples_per_second": 79.0,
-      "eval_steps_per_second": 1.782,
+      "eval_loss": 0.5546792149543762,
+      "eval_runtime": 18.1491,
+      "eval_samples_per_second": 7.328,
+      "eval_steps_per_second": 0.165,
       "step": 34
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.2492507696151733,
+      "grad_norm": 1.223302960395813,
       "learning_rate": 1.0588235294117648e-05,
-      "loss": 0.5757,
+      "loss": 0.5764,
       "step": 40
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.1255502700805664,
+      "grad_norm": 1.0631064176559448,
       "learning_rate": 8.23529411764706e-06,
-      "loss": 0.4981,
+      "loss": 0.4993,
       "step": 50
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.42026928067207336,
-      "eval_runtime": 1.4835,
-      "eval_samples_per_second": 89.651,
-      "eval_steps_per_second": 2.022,
+      "eval_loss": 0.42078566551208496,
+      "eval_runtime": 18.1595,
+      "eval_samples_per_second": 7.324,
+      "eval_steps_per_second": 0.165,
       "step": 51
     },
     {
       "epoch": 3.5294117647058822,
-      "grad_norm": 1.2060902118682861,
+      "grad_norm": 1.1994314193725586,
       "learning_rate": 5.882352941176471e-06,
-      "loss": 0.454,
+      "loss": 0.455,
       "step": 60
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.9624060150375939,
-      "eval_loss": 0.36091193556785583,
-      "eval_runtime": 1.5121,
-      "eval_samples_per_second": 87.956,
-      "eval_steps_per_second": 1.984,
+      "eval_loss": 0.3615361154079437,
+      "eval_runtime": 18.2494,
+      "eval_samples_per_second": 7.288,
+      "eval_steps_per_second": 0.164,
       "step": 68
     },
     {
       "epoch": 4.117647058823529,
-      "grad_norm": 1.07310152053833,
+      "grad_norm": 1.0398813486099243,
       "learning_rate": 3.529411764705883e-06,
-      "loss": 0.3907,
+      "loss": 0.3916,
       "step": 70
     },
     {
       "epoch": 4.705882352941177,
-      "grad_norm": 1.1172277927398682,
+      "grad_norm": 1.11141836643219,
       "learning_rate": 1.1764705882352942e-06,
-      "loss": 0.3922,
+      "loss": 0.3931,
       "step": 80
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.3435966670513153,
-      "eval_runtime": 1.6613,
-      "eval_samples_per_second": 80.057,
-      "eval_steps_per_second": 1.806,
+      "eval_accuracy": 0.9624060150375939,
+      "eval_loss": 0.34422725439071655,
+      "eval_runtime": 10.0226,
+      "eval_samples_per_second": 13.27,
+      "eval_steps_per_second": 0.299,
       "step": 85
     },
     {
       "epoch": 5.0,
       "step": 85,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 0.5855801442090203,
-      "train_runtime": 115.6504,
-      "train_samples_per_second": 44.704,
-      "train_steps_per_second": 0.735
+      "train_loss": 0.5861698781742769,
+      "train_runtime": 731.5711,
+      "train_samples_per_second": 7.067,
+      "train_steps_per_second": 0.116
     }
   ],
   "logging_steps": 10,