End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: microsoft/swinv2-large-patch4-window12-192-22k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -18,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.2293
 - Loss: 4.8090
-- Max Memory Allocated (gb): 60.24
-- Memory Allocated (gb): 3.2
+- Accuracy: 0.2293
+- Memory Allocated (gb): 1.84
+- Max Memory Allocated (gb): 58.8
 - Total Memory Available (gb): 94.62
 
 ## Model description

all_results.json

@@ -2,15 +2,15 @@
     "epoch": 30.0,
     "eval_accuracy": 0.22931691219483877,
     "eval_loss": 4.809002876281738,
-    "eval_runtime": 1131.7537,
-    "eval_samples_per_second": 593.607,
-    "eval_steps_per_second": 0.581,
-    "max_memory_allocated (GB)": 60.24,
-    "memory_allocated (GB)": 3.15,
+    "eval_runtime": 1140.029,
+    "eval_samples_per_second": 589.298,
+    "eval_steps_per_second": 0.576,
+    "max_memory_allocated (GB)": 58.8,
+    "memory_allocated (GB)": 1.84,
     "total_flos": 2.9333313524800244e+21,
     "total_memory_available (GB)": 94.62,
-    "train_loss": 1.2262731756310001,
-    "train_runtime": 56290.0261,
-    "train_samples_per_second": 358.048,
-    "train_steps_per_second": 0.35
+    "train_loss": 0.0,
+    "train_runtime": 0.2168,
+    "train_samples_per_second": 92964947.027,
+    "train_steps_per_second": 90914.595
 }

config.json

@@ -31050,6 +31050,7 @@
     0,
     0
   ],
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "stage_names": [
     "stem",

eval_results.json

@@ -2,10 +2,10 @@
     "epoch": 30.0,
     "eval_accuracy": 0.22931691219483877,
     "eval_loss": 4.809002876281738,
-    "eval_runtime": 1131.7537,
-    "eval_samples_per_second": 593.607,
-    "eval_steps_per_second": 0.581,
-    "max_memory_allocated (GB)": 60.24,
-    "memory_allocated (GB)": 3.15,
+    "eval_runtime": 1140.029,
+    "eval_samples_per_second": 589.298,
+    "eval_steps_per_second": 0.576,
+    "max_memory_allocated (GB)": 58.8,
+    "memory_allocated (GB)": 1.84,
     "total_memory_available (GB)": 94.62
 }

train_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 30.0,
-    "max_memory_allocated (GB)": 60.24,
-    "memory_allocated (GB)": 3.2,
+    "max_memory_allocated (GB)": 1.42,
+    "memory_allocated (GB)": 1.42,
     "total_flos": 2.9333313524800244e+21,
     "total_memory_available (GB)": 94.62,
-    "train_loss": 1.2262731756310001,
-    "train_runtime": 56290.0261,
-    "train_samples_per_second": 358.048,
-    "train_steps_per_second": 0.35
+    "train_loss": 0.0,
+    "train_runtime": 0.2168,
+    "train_samples_per_second": 92964947.027,
+    "train_steps_per_second": 90914.595
 }

trainer_state.json

@@ -760,15 +760,15 @@
     },
     {
       "epoch": 30.0,
-      "max_memory_allocated (GB)": 60.24,
-      "memory_allocated (GB)": 3.2,
+      "max_memory_allocated (GB)": 1.42,
+      "memory_allocated (GB)": 1.42,
       "step": 19710,
       "total_flos": 2.9333313524800244e+21,
       "total_memory_available (GB)": 94.62,
-      "train_loss": 1.2262731756310001,
-      "train_runtime": 56290.0261,
-      "train_samples_per_second": 358.048,
-      "train_steps_per_second": 0.35
+      "train_loss": 0.0,
+      "train_runtime": 0.2168,
+      "train_samples_per_second": 92964947.027,
+      "train_steps_per_second": 90914.595
     }
   ],
   "logging_steps": 500,