Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +44 -0
- preprocessor_config.json +14 -0
- pytorch_model.bin +3 -0
- runs/Jun24_05-31-43_bdef4006d530/events.out.tfevents.1687584714.bdef4006d530.45752.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +38 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "date-of-issue",
|
12 |
+
"1": "issuing-authority",
|
13 |
+
"2": "license-plate-number",
|
14 |
+
"3": "model-of-vehicle",
|
15 |
+
"4": "other",
|
16 |
+
"5": "owner",
|
17 |
+
"6": "vehicle-color"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"date-of-issue": 0,
|
23 |
+
"issuing-authority": 1,
|
24 |
+
"license-plate-number": 2,
|
25 |
+
"model-of-vehicle": 3,
|
26 |
+
"other": 4,
|
27 |
+
"owner": 5,
|
28 |
+
"vehicle-color": 6
|
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 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.30.2",
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 30522
|
44 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": false,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
|
5 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
6 |
+
"ocr_lang": null,
|
7 |
+
"processor_class": "LayoutLMv2Processor",
|
8 |
+
"resample": 2,
|
9 |
+
"size": {
|
10 |
+
"height": 224,
|
11 |
+
"width": 224
|
12 |
+
},
|
13 |
+
"tesseract_config": ""
|
14 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aacd1e90621e95cafca7e524b106db93c2e6c540e3076174ad79417dc2031843
|
3 |
+
size 450608389
|
runs/Jun24_05-31-43_bdef4006d530/events.out.tfevents.1687584714.bdef4006d530.45752.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc6acef7b3dc618a89ccb41910f08928282d6347d293aa57c038db5d394a5f4d
|
3 |
+
size 7051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"apply_ocr": false,
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"cls_token_box": [
|
7 |
+
0,
|
8 |
+
0,
|
9 |
+
0,
|
10 |
+
0
|
11 |
+
],
|
12 |
+
"do_basic_tokenize": true,
|
13 |
+
"do_lower_case": true,
|
14 |
+
"mask_token": "[MASK]",
|
15 |
+
"model_max_length": 512,
|
16 |
+
"never_split": null,
|
17 |
+
"only_label_first_subword": true,
|
18 |
+
"pad_token": "[PAD]",
|
19 |
+
"pad_token_box": [
|
20 |
+
0,
|
21 |
+
0,
|
22 |
+
0,
|
23 |
+
0
|
24 |
+
],
|
25 |
+
"pad_token_label": -100,
|
26 |
+
"processor_class": "LayoutLMv2Processor",
|
27 |
+
"sep_token": "[SEP]",
|
28 |
+
"sep_token_box": [
|
29 |
+
1000,
|
30 |
+
1000,
|
31 |
+
1000,
|
32 |
+
1000
|
33 |
+
],
|
34 |
+
"strip_accents": null,
|
35 |
+
"tokenize_chinese_chars": true,
|
36 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
37 |
+
"unk_token": "[UNK]"
|
38 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f7c17005f1ed655ce83dbfe9785a6671bc87a142bef13af0ed6b089035b8020
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|