jordyvl commited on
Commit
627d912
1 Parent(s): f2f9df5

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "EE_config": {
3
+ "apply_ocr": true,
4
+ "batch_size": 1,
5
+ "checkpoint": "",
6
+ "data_parallel": false,
7
+ "dataset": "rvl-cdip_single_10",
8
+ "device": "cuda",
9
+ "downsampling": 0,
10
+ "epochs": 1,
11
+ "eval_start": false,
12
+ "forward_signature": [
13
+ "input_ids",
14
+ "attention_mask",
15
+ "bbox",
16
+ "pixel_values",
17
+ "labels",
18
+ "token_type_ids",
19
+ "position_ids",
20
+ "head_mask",
21
+ "inputs_embeds",
22
+ "output_attentions",
23
+ "output_hidden_states",
24
+ "return_dict",
25
+ "kwargs"
26
+ ],
27
+ "get_raw_ocr_data": true,
28
+ "gradient_accumulation_steps": 1,
29
+ "lowercase": false,
30
+ "lr": 2e-05,
31
+ "model": "EElayoutlmv3",
32
+ "model_weights": "microsoft/layoutlmv3-base",
33
+ "optimizer": "AdamW",
34
+ "seed": 42,
35
+ "test_dataset": "jordyvl/rvl_cdip_100_examples_per_class",
36
+ "use_images": true,
37
+ "warmup_ratio": 0,
38
+ "weight_decay": 0
39
+ },
40
+ "_name_or_path": "microsoft/layoutlmv3-base",
41
+ "architectures": [
42
+ "LayoutLMv3EEForSequenceClassification"
43
+ ],
44
+ "attention_probs_dropout_prob": 0.1,
45
+ "bos_token_id": 0,
46
+ "classifier_dropout": null,
47
+ "coordinate_size": 128,
48
+ "eos_token_id": 2,
49
+ "exit_config": {
50
+ "encoder_layer_strategy": "ramp",
51
+ "exit_head_num_layers": 2,
52
+ "exits": [
53
+ "text_avg",
54
+ "vision_avg",
55
+ 1,
56
+ 4,
57
+ 8
58
+ ],
59
+ "global_threshold": 0.9,
60
+ "inference_strategy": "max_confidence",
61
+ "training_strategy": "joint_weighted_avg"
62
+ },
63
+ "has_relative_attention_bias": true,
64
+ "has_spatial_attention_bias": true,
65
+ "hidden_act": "gelu",
66
+ "hidden_dropout_prob": 0.1,
67
+ "hidden_size": 768,
68
+ "id2label": {
69
+ "0": "letter",
70
+ "1": "form",
71
+ "2": "email",
72
+ "3": "handwritten",
73
+ "4": "advertisement",
74
+ "5": "scientific_report",
75
+ "6": "scientific_publication",
76
+ "7": "specification",
77
+ "8": "file_folder",
78
+ "9": "news_article",
79
+ "10": "budget",
80
+ "11": "invoice",
81
+ "12": "presentation",
82
+ "13": "questionnaire",
83
+ "14": "resume",
84
+ "15": "memo"
85
+ },
86
+ "initializer_range": 0.02,
87
+ "input_size": 224,
88
+ "intermediate_size": 3072,
89
+ "label2id": {
90
+ "advertisement": 4,
91
+ "budget": 10,
92
+ "email": 2,
93
+ "file_folder": 8,
94
+ "form": 1,
95
+ "handwritten": 3,
96
+ "invoice": 11,
97
+ "letter": 0,
98
+ "memo": 15,
99
+ "news_article": 9,
100
+ "presentation": 12,
101
+ "questionnaire": 13,
102
+ "resume": 14,
103
+ "scientific_publication": 6,
104
+ "scientific_report": 5,
105
+ "specification": 7
106
+ },
107
+ "layer_norm_eps": 1e-05,
108
+ "max_2d_position_embeddings": 1024,
109
+ "max_position_embeddings": 514,
110
+ "max_rel_2d_pos": 256,
111
+ "max_rel_pos": 128,
112
+ "model_type": "layoutlmv3",
113
+ "num_attention_heads": 12,
114
+ "num_channels": 3,
115
+ "num_hidden_layers": 12,
116
+ "pad_token_id": 1,
117
+ "patch_size": 16,
118
+ "rel_2d_pos_bins": 64,
119
+ "rel_pos_bins": 32,
120
+ "second_input_size": 112,
121
+ "shape_size": 128,
122
+ "text_embed": true,
123
+ "torch_dtype": "float32",
124
+ "transformers_version": "4.28.0.dev0",
125
+ "type_vocab_size": 1,
126
+ "visual_embed": true,
127
+ "vocab_size": 50265
128
+ }
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:e8b725e43ea346922a98c372eef08201fd146c75dcb0edb3661596b454d82876
3
+ size 515861287
runs/Apr14_13-33-19_jordy-OMEN/1681472005.0387836/events.out.tfevents.1681472005.jordy-OMEN.65419.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fdfdc113ae8db93c686d3ac0910064449fdc91a013f7ec2dcfdc77dd5054cf
3
+ size 5864
runs/Apr14_13-33-19_jordy-OMEN/events.out.tfevents.1681472005.jordy-OMEN.65419.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f89de2147df0520f3938784409d3d64f5ca95f0894d4df531184228b00acfbb
3
+ size 7219
runs/Apr14_13-33-19_jordy-OMEN/events.out.tfevents.1681472073.jordy-OMEN.65419.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e6288dd86057cf9870f3206845b7e827a81f08ab349ced22918959e4ae053f
3
+ size 606
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b299fe10eca9630d8a3c2efe1fef8becd229341faa10869f7c30e7c089a53378
3
+ size 3631
vocab.json ADDED
The diff for this file is too large to render. See raw diff