update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: layoutlmv2-large-uncased-finetuned-infovqa
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# layoutlmv2-large-uncased-finetuned-infovqa
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [microsoft/layoutlmv2-large-uncased](https://huggingface.co/microsoft/layoutlmv2-large-uncased) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.2207
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
+
- eval_batch_size: 2
|
| 39 |
+
- seed: 250500
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 2
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 4.1829 | 0.08 | 500 | 3.6339 |
|
| 49 |
+
| 3.5002 | 0.16 | 1000 | 3.0721 |
|
| 50 |
+
| 2.9556 | 0.24 | 1500 | 2.8731 |
|
| 51 |
+
| 2.8939 | 0.33 | 2000 | 3.1566 |
|
| 52 |
+
| 2.6986 | 0.41 | 2500 | 3.1023 |
|
| 53 |
+
| 2.7569 | 0.49 | 3000 | 2.7743 |
|
| 54 |
+
| 2.6391 | 0.57 | 3500 | 2.5023 |
|
| 55 |
+
| 2.4277 | 0.65 | 4000 | 2.5465 |
|
| 56 |
+
| 2.4242 | 0.73 | 4500 | 2.4709 |
|
| 57 |
+
| 2.3978 | 0.82 | 5000 | 2.4019 |
|
| 58 |
+
| 2.2653 | 0.9 | 5500 | 2.3383 |
|
| 59 |
+
| 2.3916 | 0.98 | 6000 | 2.4765 |
|
| 60 |
+
| 1.9423 | 1.06 | 6500 | 2.3798 |
|
| 61 |
+
| 1.8538 | 1.14 | 7000 | 2.3628 |
|
| 62 |
+
| 1.8136 | 1.22 | 7500 | 2.3671 |
|
| 63 |
+
| 1.7808 | 1.31 | 8000 | 2.5585 |
|
| 64 |
+
| 1.7772 | 1.39 | 8500 | 2.5862 |
|
| 65 |
+
| 1.755 | 1.47 | 9000 | 2.3105 |
|
| 66 |
+
| 1.6529 | 1.55 | 9500 | 2.2417 |
|
| 67 |
+
| 1.6956 | 1.63 | 10000 | 2.1755 |
|
| 68 |
+
| 1.5713 | 1.71 | 10500 | 2.2917 |
|
| 69 |
+
| 1.565 | 1.79 | 11000 | 2.0838 |
|
| 70 |
+
| 1.615 | 1.88 | 11500 | 2.2111 |
|
| 71 |
+
| 1.5249 | 1.96 | 12000 | 2.2207 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.12.3
|
| 77 |
+
- Pytorch 1.8.0+cu101
|
| 78 |
+
- Datasets 1.15.1
|
| 79 |
+
- Tokenizers 0.10.3
|