Training in progress, epoch 1

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
+base_model: facebook/deit-tiny-patch16-224
 tags:
 - image-classification
 - vision
@@ -8,19 +8,19 @@ tags:
 metrics:
 - accuracy
 model-index:
-- name: food101-vit-base-patch16-224-in21k
+- name: food101-deit-tiny-patch16-224
   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. -->
 
-# food101-vit-base-patch16-224-in21k
+# food101-deit-tiny-patch16-224
 
-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 food101 dataset.
+This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the food101 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3873
-- Accuracy: 0.9035
+- Loss: 0.6538
+- Accuracy: 0.8204
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.9431        | 1.0   | 9469  | 0.6777          | 0.8593   |
-| 0.617         | 2.0   | 18938 | 0.4546          | 0.8802   |
-| 0.9109        | 3.0   | 28407 | 0.4086          | 0.8899   |
-| 1.0346        | 4.0   | 37876 | 0.3911          | 0.8968   |
-| 0.2142        | 5.0   | 47345 | 0.4098          | 0.8913   |
-| 0.7247        | 6.0   | 56814 | 0.3904          | 0.9008   |
-| 0.3935        | 7.0   | 66283 | 0.3873          | 0.9035   |
-| 0.552         | 8.0   | 75752 | 0.3915          | 0.9053   |
-| 0.4012        | 9.0   | 85221 | 0.3955          | 0.9052   |
-| 0.2699        | 10.0  | 94690 | 0.3894          | 0.9072   |
+| 1.7988        | 1.0   | 9469  | 1.4392          | 0.6555   |
+| 1.5581        | 2.0   | 18938 | 1.1165          | 0.7145   |
+| 1.2981        | 3.0   | 28407 | 0.9254          | 0.7558   |
+| 1.4347        | 4.0   | 37876 | 0.8343          | 0.7739   |
+| 0.9679        | 5.0   | 47345 | 0.7731          | 0.7922   |
+| 0.9975        | 6.0   | 56814 | 0.7378          | 0.7998   |
+| 1.0269        | 7.0   | 66283 | 0.7022          | 0.8073   |
+| 0.8969        | 8.0   | 75752 | 0.6865          | 0.8117   |
+| 0.8152        | 9.0   | 85221 | 0.6641          | 0.8194   |
+| 0.7437        | 10.0  | 94690 | 0.6538          | 0.8204   |
 
 
 ### Framework versions

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.9035247524752476,
-    "eval_loss": 0.38733184337615967,
-    "eval_runtime": 228.3973,
-    "eval_samples_per_second": 110.553,
-    "eval_steps_per_second": 13.822,
-    "train_loss": 0.6563277260213383,
-    "train_runtime": 13063.3743,
-    "train_samples_per_second": 57.987,
-    "train_steps_per_second": 7.249
+    "eval_accuracy": 0.8204356435643564,
+    "eval_loss": 0.6538042426109314,
+    "eval_runtime": 37.4035,
+    "eval_samples_per_second": 675.071,
+    "eval_steps_per_second": 84.404,
+    "train_loss": 1.2358400564811112,
+    "train_runtime": 3207.066,
+    "train_samples_per_second": 236.197,
+    "train_steps_per_second": 29.525
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.9035247524752476,
-    "eval_loss": 0.38733184337615967,
-    "eval_runtime": 228.3973,
-    "eval_samples_per_second": 110.553,
-    "eval_steps_per_second": 13.822
+    "eval_accuracy": 0.8204356435643564,
+    "eval_loss": 0.6538042426109314,
+    "eval_runtime": 37.4035,
+    "eval_samples_per_second": 675.071,
+    "eval_steps_per_second": 84.404
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279649f0384739453d81f52c14db03537b0f080ade4b5567844e76316e9f11df
+oid sha256:b71412d7c434692360a243d23bd206029523b5c0b937b47209e4d50bc69664b9
 size 343528508

runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723515475.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451eb57fcd068cf3b6bac42dce793c02a16c453a01dd49e69ac58311952081d2
+size 2042495

runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723518728.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0a7fba4ef31888417657d517013b9c2da43359f535138cf1d8b07dde24f5c6
+size 417

runs/Aug13_12-20-18_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723519227.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1093622.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe35b94db8478744f32a33fca1b9e1693388f1877d1ba0eb33f9f736013009d9
+size 209706

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.6563277260213383,
-    "train_runtime": 13063.3743,
-    "train_samples_per_second": 57.987,
-    "train_steps_per_second": 7.249
+    "train_loss": 1.2358400564811112,
+    "train_runtime": 3207.066,
+    "train_samples_per_second": 236.197,
+    "train_steps_per_second": 29.525
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e20e2ec6ac05af5d074b4bf2d1c6ed2480155f648dcacbcc03640ea344c8c44
+oid sha256:e9325ad33a512ccd7c6f44c7050ab82d97a980a78d164b7adef5450e838f1853
 size 5048