Upload with huggingface_hub
Browse files- config.json +110 -0
- merges.txt +0 -0
- optimizer.pt +3 -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 +84 -0
- trainer_state.json +52 -0
- training_args.bin +3 -0
- upload_after.py +14 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"EE_config": {
|
3 |
+
"apply_ocr": true,
|
4 |
+
"batch_size": 2,
|
5 |
+
"checkpoint": "",
|
6 |
+
"data_parallel": false,
|
7 |
+
"dataset": "jordyvl/rvl_cdip_100_examples_per_class",
|
8 |
+
"device": "cuda",
|
9 |
+
"downsampling": 0,
|
10 |
+
"epochs": 40,
|
11 |
+
"eval_start": false,
|
12 |
+
"forward_signature": [
|
13 |
+
"input_ids",
|
14 |
+
"attention_mask",
|
15 |
+
"token_type_ids",
|
16 |
+
"position_ids",
|
17 |
+
"head_mask",
|
18 |
+
"inputs_embeds",
|
19 |
+
"labels",
|
20 |
+
"output_attentions",
|
21 |
+
"output_hidden_states",
|
22 |
+
"return_dict",
|
23 |
+
"bbox",
|
24 |
+
"pixel_values"
|
25 |
+
],
|
26 |
+
"get_raw_ocr_data": true,
|
27 |
+
"lr": 2e-05,
|
28 |
+
"model": "LayoutLMv3",
|
29 |
+
"model_weights": "microsoft/layoutlmv3-base",
|
30 |
+
"optimizer": "AdamW",
|
31 |
+
"seed": 42,
|
32 |
+
"use_images": true,
|
33 |
+
"warmup_ratio": 0
|
34 |
+
},
|
35 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
36 |
+
"architectures": [
|
37 |
+
"LayoutLMv3ForSequenceClassification"
|
38 |
+
],
|
39 |
+
"attention_probs_dropout_prob": 0.1,
|
40 |
+
"bos_token_id": 0,
|
41 |
+
"classifier_dropout": null,
|
42 |
+
"coordinate_size": 128,
|
43 |
+
"eos_token_id": 2,
|
44 |
+
"has_relative_attention_bias": true,
|
45 |
+
"has_spatial_attention_bias": true,
|
46 |
+
"hidden_act": "gelu",
|
47 |
+
"hidden_dropout_prob": 0.1,
|
48 |
+
"hidden_size": 768,
|
49 |
+
"id2label": {
|
50 |
+
"0": "letter",
|
51 |
+
"1": "form",
|
52 |
+
"2": "email",
|
53 |
+
"3": "handwritten",
|
54 |
+
"4": "advertisement",
|
55 |
+
"5": "scientific_report",
|
56 |
+
"6": "scientific_publication",
|
57 |
+
"7": "specification",
|
58 |
+
"8": "file_folder",
|
59 |
+
"9": "news_article",
|
60 |
+
"10": "budget",
|
61 |
+
"11": "invoice",
|
62 |
+
"12": "presentation",
|
63 |
+
"13": "questionnaire",
|
64 |
+
"14": "resume",
|
65 |
+
"15": "memo"
|
66 |
+
},
|
67 |
+
"initializer_range": 0.02,
|
68 |
+
"input_size": 224,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"advertisement": 4,
|
72 |
+
"budget": 10,
|
73 |
+
"email": 2,
|
74 |
+
"file_folder": 8,
|
75 |
+
"form": 1,
|
76 |
+
"handwritten": 3,
|
77 |
+
"invoice": 11,
|
78 |
+
"letter": 0,
|
79 |
+
"memo": 15,
|
80 |
+
"news_article": 9,
|
81 |
+
"presentation": 12,
|
82 |
+
"questionnaire": 13,
|
83 |
+
"resume": 14,
|
84 |
+
"scientific_publication": 6,
|
85 |
+
"scientific_report": 5,
|
86 |
+
"specification": 7
|
87 |
+
},
|
88 |
+
"layer_norm_eps": 1e-05,
|
89 |
+
"max_2d_position_embeddings": 1024,
|
90 |
+
"max_position_embeddings": 514,
|
91 |
+
"max_rel_2d_pos": 256,
|
92 |
+
"max_rel_pos": 128,
|
93 |
+
"model_type": "layoutlmv3",
|
94 |
+
"num_attention_heads": 12,
|
95 |
+
"num_channels": 3,
|
96 |
+
"num_hidden_layers": 12,
|
97 |
+
"pad_token_id": 1,
|
98 |
+
"patch_size": 16,
|
99 |
+
"problem_type": "single_label_classification",
|
100 |
+
"rel_2d_pos_bins": 64,
|
101 |
+
"rel_pos_bins": 32,
|
102 |
+
"second_input_size": 112,
|
103 |
+
"shape_size": 128,
|
104 |
+
"text_embed": true,
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.28.0.dev0",
|
107 |
+
"type_vocab_size": 1,
|
108 |
+
"visual_embed": true,
|
109 |
+
"vocab_size": 50265
|
110 |
+
}
|
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:f8989f5fc2735b982038db41895f98e7f4d3a261010acfcf864792e499c91e42
|
3 |
+
size 1007564321
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69456733fb84bafddb8fd81b5fe5b4eaaa368b44681bbe308709ade6777f41d1
|
3 |
+
size 503796623
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953ed6ec47a3b12b7e5ca72e8b5ffcfaaca444fca8c1ba2f7d9da4b46feb4f93
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7c4b21ce0b51acc0a20c5c98ae6476c62e5e7fea8cbdb49a2c9394605a1582a
|
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 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"only_label_first_subword": true,
|
44 |
+
"pad_token": {
|
45 |
+
"__type": "AddedToken",
|
46 |
+
"content": "<pad>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
"pad_token_box": [
|
53 |
+
0,
|
54 |
+
0,
|
55 |
+
0,
|
56 |
+
0
|
57 |
+
],
|
58 |
+
"pad_token_label": -100,
|
59 |
+
"sep_token": {
|
60 |
+
"__type": "AddedToken",
|
61 |
+
"content": "</s>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false
|
66 |
+
},
|
67 |
+
"sep_token_box": [
|
68 |
+
0,
|
69 |
+
0,
|
70 |
+
0,
|
71 |
+
0
|
72 |
+
],
|
73 |
+
"special_tokens_map_file": null,
|
74 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
75 |
+
"trim_offsets": true,
|
76 |
+
"unk_token": {
|
77 |
+
"__type": "AddedToken",
|
78 |
+
"content": "<unk>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false
|
83 |
+
}
|
84 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 38.4,
|
5 |
+
"global_step": 480,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 8.0,
|
12 |
+
"eval_accuracy": 0.66,
|
13 |
+
"eval_loss": 1.381475567817688,
|
14 |
+
"eval_runtime": 88.5509,
|
15 |
+
"eval_samples_per_second": 4.517,
|
16 |
+
"eval_steps_per_second": 2.259,
|
17 |
+
"step": 100
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 16.0,
|
21 |
+
"eval_accuracy": 0.7775,
|
22 |
+
"eval_loss": 0.8648924231529236,
|
23 |
+
"eval_runtime": 87.4735,
|
24 |
+
"eval_samples_per_second": 4.573,
|
25 |
+
"eval_steps_per_second": 2.286,
|
26 |
+
"step": 200
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 24.0,
|
30 |
+
"eval_accuracy": 0.785,
|
31 |
+
"eval_loss": 0.9166873693466187,
|
32 |
+
"eval_runtime": 87.4248,
|
33 |
+
"eval_samples_per_second": 4.575,
|
34 |
+
"eval_steps_per_second": 2.288,
|
35 |
+
"step": 300
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 32.0,
|
39 |
+
"eval_accuracy": 0.79,
|
40 |
+
"eval_loss": 0.9467521905899048,
|
41 |
+
"eval_runtime": 89.9359,
|
42 |
+
"eval_samples_per_second": 4.448,
|
43 |
+
"eval_steps_per_second": 2.224,
|
44 |
+
"step": 400
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 480,
|
48 |
+
"num_train_epochs": 40,
|
49 |
+
"total_flos": 8154344545320960.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2ad9a6c5cd5621992ad42fd7ad0be421684ae345176053f222ea68597cd667
|
3 |
+
size 3631
|
upload_after.py
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from huggingface_hub import create_repo
|
2 |
+
|
3 |
+
identifier = "jordyvl/LayoutLMv3_RVL-CDIP_NK100"
|
4 |
+
# create_repo(identifier)
|
5 |
+
|
6 |
+
from huggingface_hub import HfApi
|
7 |
+
|
8 |
+
api = HfApi()
|
9 |
+
|
10 |
+
api.upload_folder(
|
11 |
+
folder_path="/home/jordy/code/opensource/Beyond-Document-Page-Classification/src/EE/test_LayoutLMv3_jordyvl/rvl_cdip_100_examples_per_class_2023-04-04 11:38/checkpoint-480",
|
12 |
+
repo_id=identifier,
|
13 |
+
repo_type="model",
|
14 |
+
)
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|