SJChaudhuri
/

beit-base-patch16-224-pt22k-finetuned-IDRiD

Image Classification

Transformers

PyTorch

TensorBoard

beit

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

SJChaudhuri commited on Apr 1, 2024

Commit

42961b3

1 Parent(s): dc308af

update model card README.md

Browse files

Files changed (1) hide show

README.md +13 -23

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9911
-- Accuracy: 0.6190
 ## Model description
@@ -45,32 +45,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 3    | 1.3246          | 0.4762   |
-| No log        | 2.0   | 6    | 1.3623          | 0.2857   |
-| No log        | 3.0   | 9    | 1.2266          | 0.5      |
-| 1.4927        | 4.0   | 12   | 1.1883          | 0.5238   |
-| 1.4927        | 5.0   | 15   | 1.1602          | 0.5476   |
-| 1.4927        | 6.0   | 18   | 1.1061          | 0.5476   |
-| 1.2358        | 7.0   | 21   | 1.1068          | 0.5      |
-| 1.2358        | 8.0   | 24   | 1.0988          | 0.5952   |
-| 1.2358        | 9.0   | 27   | 0.9244          | 0.5714   |
-| 1.0867        | 10.0  | 30   | 1.1630          | 0.5476   |
-| 1.0867        | 11.0  | 33   | 0.9561          | 0.5      |
-| 1.0867        | 12.0  | 36   | 1.2424          | 0.5      |
-| 1.0867        | 13.0  | 39   | 0.8336          | 0.5952   |
-| 0.9834        | 14.0  | 42   | 0.9911          | 0.6190   |
-| 0.9834        | 15.0  | 45   | 0.9701          | 0.5476   |
-| 0.9834        | 16.0  | 48   | 0.8365          | 0.5952   |
-| 0.9604        | 17.0  | 51   | 0.8691          | 0.5      |
-| 0.9604        | 18.0  | 54   | 0.9503          | 0.5476   |
-| 0.9604        | 19.0  | 57   | 0.9222          | 0.5476   |
-| 0.8664        | 20.0  | 60   | 0.9122          | 0.5476   |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1881
+- Accuracy: 0.5714
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 3    | 1.5369          | 0.4762   |
+| No log        | 2.0   | 6    | 1.4999          | 0.3333   |
+| No log        | 3.0   | 9    | 1.3085          | 0.4524   |
+| 1.6051        | 4.0   | 12   | 1.3072          | 0.4524   |
+| 1.6051        | 5.0   | 15   | 1.2578          | 0.5238   |
+| 1.6051        | 6.0   | 18   | 1.2376          | 0.5476   |
+| 1.3665        | 7.0   | 21   | 1.2073          | 0.5714   |
+| 1.3665        | 8.0   | 24   | 1.1972          | 0.5714   |
+| 1.3665        | 9.0   | 27   | 1.1942          | 0.5714   |
+| 1.3024        | 10.0  | 30   | 1.1881          | 0.5714   |
 ### Framework versions