End of training

README.md

@@ -3,12 +3,29 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: models_diff
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 1.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 # models_diff
 
 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 imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0001
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 500.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.00011338650074321777,
-    "eval_runtime": 1.0132,
-    "eval_samples_per_second": 99.684,
-    "eval_steps_per_second": 6.909,
+    "eval_runtime": 2.5564,
+    "eval_samples_per_second": 39.508,
+    "eval_steps_per_second": 2.738,
     "total_flos": 2.208521704015872e+19,
-    "train_loss": 0.04609681815571255,
-    "train_runtime": 3784.0996,
-    "train_samples_per_second": 75.315,
-    "train_steps_per_second": 4.757
+    "train_loss": 0.0,
+    "train_runtime": 1.8559,
+    "train_samples_per_second": 153560.694,
+    "train_steps_per_second": 9698.57
 }

config.json

@@ -26,6 +26,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 500.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.00011338650074321777,
-    "eval_runtime": 1.0132,
-    "eval_samples_per_second": 99.684,
-    "eval_steps_per_second": 6.909
+    "eval_runtime": 2.5564,
+    "eval_samples_per_second": 39.508,
+    "eval_steps_per_second": 2.738
 }

runs/Dec30_13-29-10_gpu-cv/events.out.tfevents.1735561782.gpu-cv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7db7f73c00bc7b6b0c8b35b527c5749bd8e20906cccbf814512908f06ac9983
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 500.0,
     "total_flos": 2.208521704015872e+19,
-    "train_loss": 0.04609681815571255,
-    "train_runtime": 3784.0996,
-    "train_samples_per_second": 75.315,
-    "train_steps_per_second": 4.757
+    "train_loss": 0.0,
+    "train_runtime": 1.8559,
+    "train_samples_per_second": 153560.694,
+    "train_steps_per_second": 9698.57
 }

trainer_state.json

@@ -264,10 +264,10 @@
       "epoch": 500.0,
       "step": 18000,
       "total_flos": 2.208521704015872e+19,
-      "train_loss": 0.04609681815571255,
-      "train_runtime": 3784.0996,
-      "train_samples_per_second": 75.315,
-      "train_steps_per_second": 4.757
+      "train_loss": 0.0,
+      "train_runtime": 1.8559,
+      "train_samples_per_second": 153560.694,
+      "train_steps_per_second": 9698.57
     }
   ],
   "logging_steps": 500,