jonastokoliu
/

image_caption_git-base_pokemon-blip-captions_finetune

Image-Text-to-Text

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

jonastokoliu commited on May 28, 2023

Commit

3f01309

•

1 Parent(s): 02f0973

update model card README.md

Files changed (1) hide show

README.md +14 -14

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/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0352
-- Wer Score: 2.7913
 ## Model description
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 7.2035        | 4.17  | 50   | 4.4675          | 19.6556   |
-| 2.3254        | 8.33  | 100  | 0.4499          | 10.5941   |
-| 0.1373        | 12.5  | 150  | 0.0313          | 0.9117    |
-| 0.016         | 16.67 | 200  | 0.0285          | 3.4968    |
-| 0.005         | 20.83 | 250  | 0.0307          | 3.3585    |
-| 0.002         | 25.0  | 300  | 0.0328          | 3.2420    |
-| 0.0013        | 29.17 | 350  | 0.0341          | 3.1921    |
-| 0.0011        | 33.33 | 400  | 0.0342          | 2.8963    |
-| 0.0011        | 37.5  | 450  | 0.0347          | 2.8335    |
-| 0.001         | 41.67 | 500  | 0.0349          | 2.8003    |
-| 0.0009        | 45.83 | 550  | 0.0351          | 2.7823    |
-| 0.0009        | 50.0  | 600  | 0.0352          | 2.7913    |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0382
+- Wer Score: 2.2973
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 7.1973        | 4.17  | 50   | 4.4470          | 21.4968   |
+| 2.3075        | 8.33  | 100  | 0.4412          | 10.5882   |
+| 0.1359        | 12.5  | 150  | 0.0328          | 1.5792    |
+| 0.0188        | 16.67 | 200  | 0.0293          | 1.1776    |
+| 0.0068        | 20.83 | 250  | 0.0329          | 2.0798    |
+| 0.0023        | 25.0  | 300  | 0.0354          | 2.6898    |
+| 0.0014        | 29.17 | 350  | 0.0365          | 2.5650    |
+| 0.0012        | 33.33 | 400  | 0.0374          | 2.4118    |
+| 0.0011        | 37.5  | 450  | 0.0377          | 2.4080    |
+| 0.001         | 41.67 | 500  | 0.0381          | 2.3745    |
+| 0.0009        | 45.83 | 550  | 0.0382          | 2.2857    |
+| 0.0009        | 50.0  | 600  | 0.0382          | 2.2973    |
 ### Framework versions