DUNHILL
/

results_outputs

Visual Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

DUNHILL commited on Oct 21, 2024

Commit

c84fec6

·

verified ·

1 Parent(s): 5d9a646

Model save

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9076
-- Accuracy: 0.375
 ## Model description
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5748        | 1.0   | 125  | 0.7199          | 0.92     |
-| 0.7339        | 2.0   | 250  | 0.6890          | 0.92     |
-| 0.728         | 3.0   | 375  | 0.7894          | 0.255    |
-| 0.3861        | 4.0   | 500  | 0.8479          | 0.305    |
-| 0.1705        | 5.0   | 625  | 0.9076          | 0.375    |
 ### Framework versions

 This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.9943
+- Accuracy: 0.63
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5853        | 1.0   | 125  | 0.7203          | 0.92     |
+| 0.7268        | 2.0   | 250  | 0.6818          | 0.92     |
+| 0.6477        | 3.0   | 375  | 0.7565          | 0.715    |
+| 0.2816        | 4.0   | 500  | 0.9305          | 0.7      |
+| 0.0624        | 5.0   | 625  | 0.9943          | 0.63     |
 ### Framework versions