Upload TFLayoutLMForTokenClassification
Browse files- README.md +61 -0
- config.json +43 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/layoutlm-base-uncased
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: layoutlm-funsd-tf
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# layoutlm-funsd-tf
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.4674
|
18 |
+
- Validation Loss: 0.6405
|
19 |
+
- Train Overall Precision: 0.7082
|
20 |
+
- Train Overall Recall: 0.7637
|
21 |
+
- Train Overall F1: 0.7349
|
22 |
+
- Train Overall Accuracy: 0.7984
|
23 |
+
- Epoch: 4
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
43 |
+
- training_precision: mixed_float16
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|
48 |
+
|:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
|
49 |
+
| 1.7185 | 1.4324 | 0.2236 | 0.2805 | 0.2488 | 0.5123 | 0 |
|
50 |
+
| 1.1768 | 0.9053 | 0.5468 | 0.6744 | 0.6039 | 0.7257 | 1 |
|
51 |
+
| 0.7782 | 0.6968 | 0.6512 | 0.7250 | 0.6861 | 0.7760 | 2 |
|
52 |
+
| 0.5777 | 0.6506 | 0.6826 | 0.7682 | 0.7229 | 0.7924 | 3 |
|
53 |
+
| 0.4674 | 0.6405 | 0.7082 | 0.7637 | 0.7349 | 0.7984 | 4 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.33.3
|
59 |
+
- TensorFlow 2.13.0
|
60 |
+
- Datasets 2.14.5
|
61 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlm-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "O",
|
12 |
+
"1": "B-HEADER",
|
13 |
+
"2": "I-HEADER",
|
14 |
+
"3": "B-QUESTION",
|
15 |
+
"4": "I-QUESTION",
|
16 |
+
"5": "B-ANSWER",
|
17 |
+
"6": "I-ANSWER"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"B-ANSWER": 5,
|
23 |
+
"B-HEADER": 1,
|
24 |
+
"B-QUESTION": 3,
|
25 |
+
"I-ANSWER": 6,
|
26 |
+
"I-HEADER": 2,
|
27 |
+
"I-QUESTION": 4,
|
28 |
+
"O": 0
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"max_2d_position_embeddings": 1024,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "layoutlm",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"output_past": true,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"transformers_version": "4.33.3",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 30522
|
43 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b9479756d08b478228bfdf5eed408982ab9decc92cf68ff8a82642a6e97893
|
3 |
+
size 450829256
|