🍻 cheers

README.md

@@ -4,8 +4,6 @@ base_model: openai/clip-vit-base-patch32
 tags:
 - image-classification
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: logo-matching-base
   results: []
@@ -18,8 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the ellabettison/logo-matching dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0550
-- Accuracy: 0.2770
+- eval_loss: 0.0342
+- eval_accuracy: 0.2435
+- eval_runtime: 128.298
+- eval_samples_per_second: 4.193
+- eval_steps_per_second: 0.53
+- epoch: 4.9362
+- step: 232
 
 ## Model description
 
@@ -46,22 +49,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 10
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.014         | 1.0   | 47   | 0.0481          | 0.2881   |
-| 0.0127        | 2.0   | 94   | 0.0544          | 0.1284   |
-| 0.0097        | 3.0   | 141  | 0.0565          | 0.1339   |
-| 0.0062        | 4.0   | 188  | 0.0624          | 0.1670   |
-| 0.0051        | 5.0   | 235  | 0.0594          | 0.2367   |
-| 0.0037        | 6.0   | 282  | 0.0646          | 0.2092   |
-| 0.0023        | 7.0   | 329  | 0.0665          | 0.1982   |
-| 0.0015        | 8.0   | 376  | 0.0688          | 0.1596   |
-| 0.0013        | 9.0   | 423  | 0.0706          | 0.1817   |
-| 0.0007        | 10.0  | 470  | 0.0712          | 0.1743   |
-
-
 ### Framework versions
 
 - Transformers 4.47.1

all_results.json

@@ -1,13 +1,4 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.27695167286245354,
-    "eval_loss": 0.055018216371536255,
-    "eval_runtime": 5.4841,
-    "eval_samples_per_second": 98.101,
-    "eval_steps_per_second": 12.399,
-    "total_flos": 5.916629591779738e+17,
-    "train_loss": 0.006165030080468413,
-    "train_runtime": 454.1808,
-    "train_samples_per_second": 16.469,
-    "train_steps_per_second": 1.035
+    "eval_accuracy": 0.24349442379182157,
+    "eval_loss": 0.034249916672706604
 }

eval_results.json

@@ -1,8 +1,4 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.27695167286245354,
-    "eval_loss": 0.055018216371536255,
-    "eval_runtime": 5.4841,
-    "eval_samples_per_second": 98.101,
-    "eval_steps_per_second": 12.399
+    "eval_accuracy": 0.24349442379182157,
+    "eval_loss": 0.034249916672706604
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fcdf933f3df64a20e97034b9c84a575d91f9f7b57a54e92de1b1c9d99be4411
+oid sha256:4d2cbac053bb89674548b7d77465dd6f3a79717adb16ca5044c01f8ea2135d20
 size 350497036

runs/Jan15_20-52-25_3d60fa82d02d/events.out.tfevents.1736974350.3d60fa82d02d.1199.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031f138e8dc638c16d4f98096a84f5a7072e0a33c8549a99804a693c44175183
-size 21723
+oid sha256:b927f1a201c061db31f03f14f28d0095b604c419414cff064149a3921ca5d656
+size 23101