End of training

README.md

@@ -3,7 +3,11 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-base-patch16-224-in21k
   results: []
@@ -14,7 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-patch16-224-in21k
 
-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 chainyo/rvl-cdip dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Accuracy: 0.0630
+- Memory Allocated (gb): 1.53
+- Max Memory Allocated (gb): 1.61
+- Total Memory Available (gb): 126.62
 
 ## Model description
 

all_results.json

@@ -2,15 +2,15 @@
     "epoch": 3.0,
     "eval_accuracy": 0.06302083333333333,
     "eval_loss": NaN,
-    "eval_runtime": 239.9792,
-    "eval_samples_per_second": 200.017,
-    "eval_steps_per_second": 3.125,
-    "max_memory_allocated (GB)": 0.97,
-    "memory_allocated (GB)": 0.97,
+    "eval_runtime": 242.9557,
+    "eval_samples_per_second": 197.567,
+    "eval_steps_per_second": 3.087,
+    "max_memory_allocated (GB)": 1.61,
+    "memory_allocated (GB)": 1.53,
     "total_flos": 6.324139790696448e+19,
     "total_memory_available (GB)": 126.62,
     "train_loss": 0.0,
-    "train_runtime": 81.7036,
-    "train_samples_per_second": 9987.288,
-    "train_steps_per_second": 1248.416
+    "train_runtime": 0.0058,
+    "train_samples_per_second": 140961263.636,
+    "train_steps_per_second": 17620222.735
 }

config.json

@@ -54,6 +54,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2"

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 3.0,
     "eval_accuracy": 0.06302083333333333,
     "eval_loss": NaN,
-    "eval_runtime": 239.9792,
-    "eval_samples_per_second": 200.017,
-    "eval_steps_per_second": 3.125,
+    "eval_runtime": 242.9557,
+    "eval_samples_per_second": 197.567,
+    "eval_steps_per_second": 3.087,
     "max_memory_allocated (GB)": 1.61,
     "memory_allocated (GB)": 1.53,
     "total_memory_available (GB)": 126.62

runs/Nov06_05-38-19_gtown-28NZK54/events.out.tfevents.1730871752.gtown-28NZK54.8152.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6145d9b31fb5311809ed1dfa5cdf319e7b3bf62bf29e4339f335cffc11ebdc3
+size 580

train_results.json

@@ -5,7 +5,7 @@
     "total_flos": 6.324139790696448e+19,
     "total_memory_available (GB)": 126.62,
     "train_loss": 0.0,
-    "train_runtime": 81.7036,
-    "train_samples_per_second": 9987.288,
-    "train_steps_per_second": 1248.416
+    "train_runtime": 0.0058,
+    "train_samples_per_second": 140961263.636,
+    "train_steps_per_second": 17620222.735
 }

trainer_state.json

@@ -2056,9 +2056,9 @@
       "total_flos": 6.324139790696448e+19,
       "total_memory_available (GB)": 126.62,
       "train_loss": 0.0,
-      "train_runtime": 81.7036,
-      "train_samples_per_second": 9987.288,
-      "train_steps_per_second": 1248.416
+      "train_runtime": 0.0058,
+      "train_samples_per_second": 140961263.636,
+      "train_steps_per_second": 17620222.735
     }
   ],
   "logging_steps": 500,