End of training
Browse files- .gitignore +1 -0
- config.json +47 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Oct14_14-58-55_pc/1665752353.8861961/events.out.tfevents.1665752353.pc.35098.1 +3 -0
- runs/Oct14_14-58-55_pc/events.out.tfevents.1665752353.pc.35098.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +85 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-HEADER",
|
17 |
+
"2": "I-HEADER",
|
18 |
+
"3": "B-QUESTION",
|
19 |
+
"4": "I-QUESTION",
|
20 |
+
"5": "B-ANSWER",
|
21 |
+
"6": "I-ANSWER"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"B-ANSWER": 5,
|
27 |
+
"B-HEADER": 1,
|
28 |
+
"B-QUESTION": 3,
|
29 |
+
"I-ANSWER": 6,
|
30 |
+
"I-HEADER": 2,
|
31 |
+
"I-QUESTION": 4,
|
32 |
+
"O": 0
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-05,
|
35 |
+
"max_2d_position_embeddings": 1024,
|
36 |
+
"max_position_embeddings": 514,
|
37 |
+
"model_type": "lilt",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.24.0.dev0",
|
44 |
+
"type_vocab_size": 1,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 50265
|
47 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580d5f6c12b0d29c69a28c5a409622f9e0308339ac8b4f5a4e8a53ec15a6bd08
|
3 |
+
size 520818271
|
runs/Oct14_14-58-55_pc/1665752353.8861961/events.out.tfevents.1665752353.pc.35098.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a513130f3fb0be5f8f367bd84c9a7ce08759e6a714bd207103c284c17cabb07
|
3 |
+
size 5524
|
runs/Oct14_14-58-55_pc/events.out.tfevents.1665752353.pc.35098.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9ba85bc51363d0338b46f2a0adef59dafe586342b457494f6f27727175bf94e
|
3 |
+
size 4136
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"cls_token_box": [
|
20 |
+
0,
|
21 |
+
0,
|
22 |
+
0,
|
23 |
+
0
|
24 |
+
],
|
25 |
+
"eos_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "</s>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"errors": "replace",
|
34 |
+
"mask_token": {
|
35 |
+
"__type": "AddedToken",
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"model_max_length": 512,
|
43 |
+
"name_or_path": "microsoft/layoutlmv3-base",
|
44 |
+
"only_label_first_subword": true,
|
45 |
+
"pad_token": {
|
46 |
+
"__type": "AddedToken",
|
47 |
+
"content": "<pad>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
},
|
53 |
+
"pad_token_box": [
|
54 |
+
0,
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0
|
58 |
+
],
|
59 |
+
"pad_token_label": -100,
|
60 |
+
"sep_token": {
|
61 |
+
"__type": "AddedToken",
|
62 |
+
"content": "</s>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false
|
67 |
+
},
|
68 |
+
"sep_token_box": [
|
69 |
+
0,
|
70 |
+
0,
|
71 |
+
0,
|
72 |
+
0
|
73 |
+
],
|
74 |
+
"special_tokens_map_file": null,
|
75 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
76 |
+
"trim_offsets": true,
|
77 |
+
"unk_token": {
|
78 |
+
"__type": "AddedToken",
|
79 |
+
"content": "<unk>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false
|
84 |
+
}
|
85 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f73e1c768ac5de36176a2db0c2293695941680eb11e95a75d0af510fcc35c85
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|