Duplicate from nielsr/layoutlmv2-finetuned-funsd
Browse filesCo-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
- .gitattributes +17 -0
- .gitignore +1 -0
- README.md +61 -0
- config.json +59 -0
- preprocessor_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/Jul09_13-10-53_0589b24a56c9/1625836259.3002846/events.out.tfevents.1625836259.0589b24a56c9.1885.3 +3 -0
- runs/Jul09_13-10-53_0589b24a56c9/events.out.tfevents.1625836259.0589b24a56c9.1885.2 +3 -0
- runs/Jul09_13-14-13_0589b24a56c9/1625836458.8067036/events.out.tfevents.1625836458.0589b24a56c9.2651.1 +3 -0
- runs/Jul09_13-14-13_0589b24a56c9/events.out.tfevents.1625836458.0589b24a56c9.2651.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- funsd
|
6 |
+
model_index:
|
7 |
+
- name: layoutlmv2-finetuned-funsd
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Token Classification
|
11 |
+
type: token-classification
|
12 |
+
dataset:
|
13 |
+
name: funsd
|
14 |
+
type: funsd
|
15 |
+
args: funsd
|
16 |
+
duplicated_from: nielsr/layoutlmv2-finetuned-funsd
|
17 |
+
---
|
18 |
+
|
19 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
20 |
+
should probably proofread and complete it, then remove this comment. -->
|
21 |
+
|
22 |
+
# layoutlmv2-finetuned-funsd
|
23 |
+
|
24 |
+
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the funsd dataset.
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 8
|
45 |
+
- eval_batch_size: 8
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- training_steps: 1000
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.9.0.dev0
|
59 |
+
- Pytorch 1.8.0+cu101
|
60 |
+
- Datasets 1.9.0
|
61 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlmv2-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"convert_sync_batchnorm": true,
|
8 |
+
"coordinate_size": 128,
|
9 |
+
"fast_qkv": true,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"has_relative_attention_bias": true,
|
12 |
+
"has_spatial_attention_bias": true,
|
13 |
+
"has_visual_segment_embedding": false,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "other",
|
19 |
+
"1": "b-header",
|
20 |
+
"2": "i-header",
|
21 |
+
"3": "b-question",
|
22 |
+
"4": "i-question",
|
23 |
+
"5": "b-answer",
|
24 |
+
"6": "i-answer"
|
25 |
+
},
|
26 |
+
"image_feature_pool_shape": [
|
27 |
+
7,
|
28 |
+
7,
|
29 |
+
256
|
30 |
+
],
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 3072,
|
33 |
+
"label2id": {
|
34 |
+
"other": 0,
|
35 |
+
"b-header": 1,
|
36 |
+
"i-header": 2,
|
37 |
+
"b-question": 3,
|
38 |
+
"i-question": 4,
|
39 |
+
"b-answer": 5,
|
40 |
+
"i-answer": 6
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-12,
|
43 |
+
"max_2d_position_embeddings": 1024,
|
44 |
+
"max_position_embeddings": 512,
|
45 |
+
"max_rel_2d_pos": 256,
|
46 |
+
"max_rel_pos": 128,
|
47 |
+
"model_type": "layoutlmv2",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_hidden_layers": 12,
|
50 |
+
"output_past": true,
|
51 |
+
"pad_token_id": 0,
|
52 |
+
"rel_2d_pos_bins": 64,
|
53 |
+
"rel_pos_bins": 32,
|
54 |
+
"shape_size": 128,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.9.0.dev0",
|
57 |
+
"type_vocab_size": 2,
|
58 |
+
"vocab_size": 30522
|
59 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
|
5 |
+
"resample": 2,
|
6 |
+
"size": 224
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1460b3652dbd260b7c7194239762cf7e4944ebf15191dbf4d32598fb1403dc
|
3 |
+
size 802275154
|
runs/Jul09_13-10-53_0589b24a56c9/1625836259.3002846/events.out.tfevents.1625836259.0589b24a56c9.1885.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1a418852e3825d0dae10c046fae66f1ca419f6e13db8c11244a28822612b8f7
|
3 |
+
size 4275
|
runs/Jul09_13-10-53_0589b24a56c9/events.out.tfevents.1625836259.0589b24a56c9.1885.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e798954df897bb5791e07019b932eec3a8fd0f28b406fb4464b60115bade94da
|
3 |
+
size 3660
|
runs/Jul09_13-14-13_0589b24a56c9/1625836458.8067036/events.out.tfevents.1625836458.0589b24a56c9.2651.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96141f511ce0fa6ce209463b936c88dcfd23810c3166814330ca554d73c57dbe
|
3 |
+
size 4275
|
runs/Jul09_13-14-13_0589b24a56c9/events.out.tfevents.1625836458.0589b24a56c9.2651.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2e7203356f7b20143a2f523d302d65a4ea6507e964002cf011e52d5483626b4
|
3 |
+
size 4328
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/layoutlmv2-base-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "LayoutLMv2Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b42ef7fa01aa9aede887c9f8a1ef5f6c8d6f0c0a1994bda972e3472ee863e35
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|