Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,15 @@ It achieves the following results on the evaluation set:
|
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
+
This DocVQA model, built on the Layout LM v2 framework, represents an initial step in a series of
|
23 |
+
experimental models aimed at document visual question answering. It's the "medium" version in a planned series,
|
24 |
+
trained on a mid-sized dataset of 5k samples (split between training and test) over 20 epochs.
|
25 |
+
The training setup was modest, employing mixed precision (fp16), with manageable batch sizes and a
|
26 |
+
focused approach to learning rate adjustment (warmup steps and weight decay). Notably, this model was
|
27 |
+
trained without external reporting tools, emphasizing internal evaluation. As the first iteration in a
|
28 |
+
progressive series that will later include medium (5k samples) and large (50k samples) models, this
|
29 |
+
version serves as a foundational experiment, setting the stage for more extensive and complex models in the
|
30 |
+
future.
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|