Update README.md
Browse files
README.md
CHANGED
@@ -11,8 +11,8 @@ pipeline_tag: image-classification
|
|
11 |
# Model Card for Model ID
|
12 |
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
|
13 |
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
-
|
15 |
-
|
16 |
|
17 |
|
18 |
## Model Details
|
@@ -44,18 +44,18 @@ A model that can detect 101 variety of food.
|
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
|
54 |
## Evaluation
|
55 |
|
56 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
|
|
11 |
# Model Card for Model ID
|
12 |
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
|
13 |
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
+
- **Evaluation loss:** 0.7166455984115601
|
15 |
+
- **Accuracy:** 0.8753663366336634
|
16 |
|
17 |
|
18 |
## Model Details
|
|
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
|
47 |
+
- **learning_rate:** 5e-05
|
48 |
+
- **train_batch_size**: 16
|
49 |
+
- **seed:** 42
|
50 |
+
- **optimizer:** Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- **lr_scheduler_type:** linear
|
52 |
+
- **num_epochs:** 1
|
53 |
|
54 |
## Evaluation
|
55 |
|
56 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
57 |
+
- **eval_loss:** 0.7166455984115601
|
58 |
+
- **eval_accuracy:** 0.8753663366336634
|
59 |
+
- **eval_runtime:** 446.9362
|
60 |
+
- **eval_steps_per_second:** 3.533
|
61 |
+
- **epoch:** 1.0
|