Upload 13 files
Browse files- config.json +56 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- preprocessor_config.json +21 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +87 -0
- trainer_state.json +82 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv3ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"coordinate_size": 128,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"has_relative_attention_bias": true,
|
12 |
+
"has_spatial_attention_bias": true,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "O",
|
18 |
+
"1": "HEADER",
|
19 |
+
"2": "SUBHEADER",
|
20 |
+
"3": "TEXTO",
|
21 |
+
"4": "NUMERAL",
|
22 |
+
"5": "RESUMEN"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"input_size": 224,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"HEADER": 1,
|
29 |
+
"NUMERAL": 4,
|
30 |
+
"O": 0,
|
31 |
+
"RESUMEN": 5,
|
32 |
+
"SUBHEADER": 2,
|
33 |
+
"TEXTO": 3
|
34 |
+
},
|
35 |
+
"layer_norm_eps": 1e-05,
|
36 |
+
"max_2d_position_embeddings": 1024,
|
37 |
+
"max_position_embeddings": 514,
|
38 |
+
"max_rel_2d_pos": 256,
|
39 |
+
"max_rel_pos": 128,
|
40 |
+
"model_type": "layoutlmv3",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_channels": 3,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"pad_token_id": 1,
|
45 |
+
"patch_size": 16,
|
46 |
+
"rel_2d_pos_bins": 64,
|
47 |
+
"rel_pos_bins": 32,
|
48 |
+
"second_input_size": 112,
|
49 |
+
"shape_size": 128,
|
50 |
+
"text_embed": true,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.23.1",
|
53 |
+
"type_vocab_size": 1,
|
54 |
+
"visual_embed": true,
|
55 |
+
"vocab_size": 50265
|
56 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94bb88bf3be3e6ce988fb23e4ca4a6b3aed019296c6d00eb45c9d699d9a948fe
|
3 |
+
size 1002776809
|
preprocessor_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"feature_extractor_type": "LayoutLMv3FeatureExtractor",
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"ocr_lang": null,
|
17 |
+
"processor_class": "LayoutLMv3Processor",
|
18 |
+
"resample": 2,
|
19 |
+
"size": 224,
|
20 |
+
"tesseract_config": ""
|
21 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f34e0ac3995c5a6ce2359620b523c8036fa1ca34e418c5be2ca65964f024f5d
|
3 |
+
size 501402835
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9337b7ce0f84133ea4ae4247f72cd529182ad372b80f6d79a89834ebce736a2b
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9d6fac3218ea2ddebd5c16aee8f584831c06fbfbe02dd90573ca33ea804f1d
|
3 |
+
size 623
|
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 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"apply_ocr": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"cls_token_box": [
|
21 |
+
0,
|
22 |
+
0,
|
23 |
+
0,
|
24 |
+
0
|
25 |
+
],
|
26 |
+
"eos_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"errors": "replace",
|
35 |
+
"mask_token": {
|
36 |
+
"__type": "AddedToken",
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false
|
42 |
+
},
|
43 |
+
"model_max_length": 512,
|
44 |
+
"name_or_path": "microsoft/layoutlmv3-base",
|
45 |
+
"only_label_first_subword": true,
|
46 |
+
"pad_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "<pad>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"pad_token_box": [
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0,
|
58 |
+
0
|
59 |
+
],
|
60 |
+
"pad_token_label": -100,
|
61 |
+
"processor_class": "LayoutLMv3Processor",
|
62 |
+
"sep_token": {
|
63 |
+
"__type": "AddedToken",
|
64 |
+
"content": "</s>",
|
65 |
+
"lstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
},
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"special_tokens_map_file": null,
|
77 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
78 |
+
"trim_offsets": true,
|
79 |
+
"unk_token": {
|
80 |
+
"__type": "AddedToken",
|
81 |
+
"content": "<unk>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
}
|
87 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "layoutlmv3-finetuned-documents/checkpoint-500",
|
4 |
+
"epoch": 500.0,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 100.0,
|
12 |
+
"eval_accuracy": 0.9957081545064378,
|
13 |
+
"eval_f1": 0.8571428571428571,
|
14 |
+
"eval_loss": 0.02892388217151165,
|
15 |
+
"eval_precision": 0.8571428571428571,
|
16 |
+
"eval_recall": 0.8571428571428571,
|
17 |
+
"eval_runtime": 0.2509,
|
18 |
+
"eval_samples_per_second": 7.973,
|
19 |
+
"eval_steps_per_second": 3.986,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 200.0,
|
24 |
+
"eval_accuracy": 1.0,
|
25 |
+
"eval_f1": 1.0,
|
26 |
+
"eval_loss": 0.000514168874360621,
|
27 |
+
"eval_precision": 1.0,
|
28 |
+
"eval_recall": 1.0,
|
29 |
+
"eval_runtime": 0.2357,
|
30 |
+
"eval_samples_per_second": 8.485,
|
31 |
+
"eval_steps_per_second": 4.242,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 300.0,
|
36 |
+
"eval_accuracy": 1.0,
|
37 |
+
"eval_f1": 1.0,
|
38 |
+
"eval_loss": 0.00031278689857572317,
|
39 |
+
"eval_precision": 1.0,
|
40 |
+
"eval_recall": 1.0,
|
41 |
+
"eval_runtime": 0.2494,
|
42 |
+
"eval_samples_per_second": 8.019,
|
43 |
+
"eval_steps_per_second": 4.01,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 400.0,
|
48 |
+
"eval_accuracy": 1.0,
|
49 |
+
"eval_f1": 1.0,
|
50 |
+
"eval_loss": 0.0002630261005833745,
|
51 |
+
"eval_precision": 1.0,
|
52 |
+
"eval_recall": 1.0,
|
53 |
+
"eval_runtime": 0.2427,
|
54 |
+
"eval_samples_per_second": 8.24,
|
55 |
+
"eval_steps_per_second": 4.12,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 500.0,
|
60 |
+
"learning_rate": 7.500000000000001e-06,
|
61 |
+
"loss": 0.042,
|
62 |
+
"step": 500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 500.0,
|
66 |
+
"eval_accuracy": 1.0,
|
67 |
+
"eval_f1": 1.0,
|
68 |
+
"eval_loss": 0.0001811975089367479,
|
69 |
+
"eval_precision": 1.0,
|
70 |
+
"eval_recall": 1.0,
|
71 |
+
"eval_runtime": 0.2418,
|
72 |
+
"eval_samples_per_second": 8.272,
|
73 |
+
"eval_steps_per_second": 4.136,
|
74 |
+
"step": 500
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"max_steps": 2000,
|
78 |
+
"num_train_epochs": 2000,
|
79 |
+
"total_flos": 659007452160000.0,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c1258d4a90525a33ef28f9d28157b53e726ce6f6126f5b58898fd45f8a751d2
|
3 |
+
size 3375
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|