End of training

README.md

@@ -2,23 +2,42 @@
 license: apache-2.0
 base_model: facebook/deit-base-distilled-patch16-224
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
 model-index:
-- name: base
+- name: "DeiT-base-DatasetDict({\n    train: Dataset({\n        features: ['img',\
+    \ 'fine_label', 'coarse_label'],\n        num_rows: 50000\n    })\n    test: Dataset({\n\
+    \        features: ['img', 'fine_label', 'coarse_label'],\n        num_rows: 10000\n\
+    \    })\n    validation: Dataset({\n        features: ['img', 'fine_label', 'coarse_label'],\n\
+    \        num_rows: 10000\n    })\n})"
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# base
-
-This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on an unknown dataset.
+# DeiT-base-DatasetDict({
+    train: Dataset({
+        features: ['img', 'fine_label', 'coarse_label'],
+        num_rows: 50000
+    })
+    test: Dataset({
+        features: ['img', 'fine_label', 'coarse_label'],
+        num_rows: 10000
+    })
+    validation: Dataset({
+        features: ['img', 'fine_label', 'coarse_label'],
+        num_rows: 10000
+    })
+})
+
+This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the cifar100 dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.906
 - Loss: 0.3054
+- Accuracy: 0.906
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 10.0,
     "eval_accuracy": 0.906,
     "eval_loss": 0.3053509294986725,
-    "eval_runtime": 173.1395,
-    "eval_samples_per_second": 57.757,
-    "eval_steps_per_second": 57.757,
+    "eval_runtime": 175.7662,
+    "eval_samples_per_second": 56.894,
+    "eval_steps_per_second": 56.894,
     "total_flos": 3.8815447523328e+19,
     "train_loss": 0.0,
-    "train_runtime": 24.522,
-    "train_samples_per_second": 20389.834,
-    "train_steps_per_second": 318.897
+    "train_runtime": 36.1375,
+    "train_samples_per_second": 13836.038,
+    "train_steps_per_second": 216.396
 }

config.json

@@ -222,6 +222,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.1"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 10.0,
     "eval_accuracy": 0.906,
     "eval_loss": 0.3053509294986725,
-    "eval_runtime": 173.1395,
-    "eval_samples_per_second": 57.757,
-    "eval_steps_per_second": 57.757
+    "eval_runtime": 175.7662,
+    "eval_samples_per_second": 56.894,
+    "eval_steps_per_second": 56.894
 }

runs/Mar02_14-41-50_04f752329dca/events.out.tfevents.1709390811.04f752329dca.283.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c1208cdb37723a8396fc5cc641298180de02118c7a73d681bd6295c943afd
+size 411

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 10.0,
     "total_flos": 3.8815447523328e+19,
     "train_loss": 0.0,
-    "train_runtime": 24.522,
-    "train_samples_per_second": 20389.834,
-    "train_steps_per_second": 318.897
+    "train_runtime": 36.1375,
+    "train_samples_per_second": 13836.038,
+    "train_steps_per_second": 216.396
 }

trainer_state.json

@@ -1039,9 +1039,9 @@
       "step": 7820,
       "total_flos": 3.8815447523328e+19,
       "train_loss": 0.0,
-      "train_runtime": 24.522,
-      "train_samples_per_second": 20389.834,
-      "train_steps_per_second": 318.897
+      "train_runtime": 36.1375,
+      "train_samples_per_second": 13836.038,
+      "train_steps_per_second": 216.396
     }
   ],
   "logging_steps": 50,