SamakovskiyVO commited on
Commit
99f7686
·
verified ·
1 Parent(s): c925565

Training in progress, step 200

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ mnist_test.csv filter=lfs diff=lfs merge=lfs -text
37
+ mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ This directory includes a few sample datasets to get you started.
2
+
3
+ * `california_housing_data*.csv` is California housing data from the 1990 US
4
+ Census; more information is available at:
5
+ https://docs.google.com/document/d/e/2PACX-1vRhYtsvc5eOR2FWNCwaBiKL6suIOrxJig8LcSBbmCbyYsayia_DvPOOBlXZ4CAlQ5nlDD8kTaIDRwrN/pub
6
+
7
+ * `mnist_*.csv` is a small sample of the
8
+ [MNIST database](https://en.wikipedia.org/wiki/MNIST_database), which is
9
+ described at: http://yann.lecun.com/exdb/mnist/
10
+
11
+ * `anscombe.json` contains a copy of
12
+ [Anscombe's quartet](https://en.wikipedia.org/wiki/Anscombe%27s_quartet); it
13
+ was originally described in
14
+
15
+ Anscombe, F. J. (1973). 'Graphs in Statistical Analysis'. American
16
+ Statistician. 27 (1): 17-21. JSTOR 2682899.
17
+
18
+ and our copy was prepared by the
19
+ [vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).
anscombe.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {"Series":"I", "X":10.0, "Y":8.04},
3
+ {"Series":"I", "X":8.0, "Y":6.95},
4
+ {"Series":"I", "X":13.0, "Y":7.58},
5
+ {"Series":"I", "X":9.0, "Y":8.81},
6
+ {"Series":"I", "X":11.0, "Y":8.33},
7
+ {"Series":"I", "X":14.0, "Y":9.96},
8
+ {"Series":"I", "X":6.0, "Y":7.24},
9
+ {"Series":"I", "X":4.0, "Y":4.26},
10
+ {"Series":"I", "X":12.0, "Y":10.84},
11
+ {"Series":"I", "X":7.0, "Y":4.81},
12
+ {"Series":"I", "X":5.0, "Y":5.68},
13
+
14
+ {"Series":"II", "X":10.0, "Y":9.14},
15
+ {"Series":"II", "X":8.0, "Y":8.14},
16
+ {"Series":"II", "X":13.0, "Y":8.74},
17
+ {"Series":"II", "X":9.0, "Y":8.77},
18
+ {"Series":"II", "X":11.0, "Y":9.26},
19
+ {"Series":"II", "X":14.0, "Y":8.10},
20
+ {"Series":"II", "X":6.0, "Y":6.13},
21
+ {"Series":"II", "X":4.0, "Y":3.10},
22
+ {"Series":"II", "X":12.0, "Y":9.13},
23
+ {"Series":"II", "X":7.0, "Y":7.26},
24
+ {"Series":"II", "X":5.0, "Y":4.74},
25
+
26
+ {"Series":"III", "X":10.0, "Y":7.46},
27
+ {"Series":"III", "X":8.0, "Y":6.77},
28
+ {"Series":"III", "X":13.0, "Y":12.74},
29
+ {"Series":"III", "X":9.0, "Y":7.11},
30
+ {"Series":"III", "X":11.0, "Y":7.81},
31
+ {"Series":"III", "X":14.0, "Y":8.84},
32
+ {"Series":"III", "X":6.0, "Y":6.08},
33
+ {"Series":"III", "X":4.0, "Y":5.39},
34
+ {"Series":"III", "X":12.0, "Y":8.15},
35
+ {"Series":"III", "X":7.0, "Y":6.42},
36
+ {"Series":"III", "X":5.0, "Y":5.73},
37
+
38
+ {"Series":"IV", "X":8.0, "Y":6.58},
39
+ {"Series":"IV", "X":8.0, "Y":5.76},
40
+ {"Series":"IV", "X":8.0, "Y":7.71},
41
+ {"Series":"IV", "X":8.0, "Y":8.84},
42
+ {"Series":"IV", "X":8.0, "Y":8.47},
43
+ {"Series":"IV", "X":8.0, "Y":7.04},
44
+ {"Series":"IV", "X":8.0, "Y":5.25},
45
+ {"Series":"IV", "X":19.0, "Y":12.50},
46
+ {"Series":"IV", "X":8.0, "Y":5.56},
47
+ {"Series":"IV", "X":8.0, "Y":7.91},
48
+ {"Series":"IV", "X":8.0, "Y":6.89}
49
+ ]
california_housing_test.csv ADDED
The diff for this file is too large to render. See raw diff
 
california_housing_train.csv ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "convert_sync_batchnorm": true,
8
+ "coordinate_size": 128,
9
+ "detectron2_config_args": {
10
+ "MODEL.ANCHOR_GENERATOR.SIZES": [
11
+ [
12
+ 32
13
+ ],
14
+ [
15
+ 64
16
+ ],
17
+ [
18
+ 128
19
+ ],
20
+ [
21
+ 256
22
+ ],
23
+ [
24
+ 512
25
+ ]
26
+ ],
27
+ "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
28
+ "MODEL.FPN.IN_FEATURES": [
29
+ "res2",
30
+ "res3",
31
+ "res4",
32
+ "res5"
33
+ ],
34
+ "MODEL.MASK_ON": true,
35
+ "MODEL.PIXEL_STD": [
36
+ 57.375,
37
+ 57.12,
38
+ 58.395
39
+ ],
40
+ "MODEL.POST_NMS_TOPK_TEST": 1000,
41
+ "MODEL.RESNETS.ASPECT_RATIOS": [
42
+ [
43
+ 0.5,
44
+ 1.0,
45
+ 2.0
46
+ ]
47
+ ],
48
+ "MODEL.RESNETS.DEPTH": 101,
49
+ "MODEL.RESNETS.NUM_GROUPS": 32,
50
+ "MODEL.RESNETS.OUT_FEATURES": [
51
+ "res2",
52
+ "res3",
53
+ "res4",
54
+ "res5"
55
+ ],
56
+ "MODEL.RESNETS.SIZES": [
57
+ [
58
+ 32
59
+ ],
60
+ [
61
+ 64
62
+ ],
63
+ [
64
+ 128
65
+ ],
66
+ [
67
+ 256
68
+ ],
69
+ [
70
+ 512
71
+ ]
72
+ ],
73
+ "MODEL.RESNETS.STRIDE_IN_1X1": false,
74
+ "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
75
+ "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
76
+ "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
77
+ "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
78
+ "MODEL.ROI_HEADS.IN_FEATURES": [
79
+ "p2",
80
+ "p3",
81
+ "p4",
82
+ "p5"
83
+ ],
84
+ "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
85
+ "MODEL.ROI_HEADS.NUM_CLASSES": 5,
86
+ "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
87
+ "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
88
+ "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
89
+ "MODEL.RPN.IN_FEATURES": [
90
+ "p2",
91
+ "p3",
92
+ "p4",
93
+ "p5",
94
+ "p6"
95
+ ],
96
+ "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
97
+ "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
98
+ "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
99
+ },
100
+ "fast_qkv": true,
101
+ "gradient_checkpointing": false,
102
+ "has_relative_attention_bias": true,
103
+ "has_spatial_attention_bias": true,
104
+ "has_visual_segment_embedding": true,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "image_feature_pool_shape": [
109
+ 7,
110
+ 7,
111
+ 256
112
+ ],
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "layer_norm_eps": 1e-12,
116
+ "max_2d_position_embeddings": 1024,
117
+ "max_position_embeddings": 512,
118
+ "max_rel_2d_pos": 256,
119
+ "max_rel_pos": 128,
120
+ "model_type": "layoutlmv2",
121
+ "num_attention_heads": 12,
122
+ "num_hidden_layers": 12,
123
+ "output_past": true,
124
+ "pad_token_id": 0,
125
+ "rel_2d_pos_bins": 64,
126
+ "rel_pos_bins": 32,
127
+ "shape_size": 128,
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.44.2",
130
+ "type_vocab_size": 2,
131
+ "vocab_size": 30522
132
+ }
mnist_test.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
3
+ size 18289443
mnist_train_small.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
3
+ size 36523880
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a550bbc133c5472412251c6238b7d1d437d615da30b5c1628b073e5faf538a5d
3
+ size 802053752
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "image_processor_type": "LayoutLMv2ImageProcessor",
5
+ "ocr_lang": null,
6
+ "processor_class": "LayoutLMv2Processor",
7
+ "resample": 2,
8
+ "size": {
9
+ "height": 224,
10
+ "width": 224
11
+ },
12
+ "tesseract_config": ""
13
+ }
runs/Nov01_18-00-15_9dcd8bd02364/events.out.tfevents.1730484021.9dcd8bd02364.2261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e9a3690d7964fcd6f96e3c067921387839b64dffb3484570a8fe6198487fa4
3
+ size 8854
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "cls_token_box": [
48
+ 0,
49
+ 0,
50
+ 0,
51
+ 0
52
+ ],
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "never_split": null,
58
+ "only_label_first_subword": true,
59
+ "pad_token": "[PAD]",
60
+ "pad_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "pad_token_label": -100,
67
+ "processor_class": "LayoutLMv2Processor",
68
+ "sep_token": "[SEP]",
69
+ "sep_token_box": [
70
+ 1000,
71
+ 1000,
72
+ 1000,
73
+ 1000
74
+ ],
75
+ "strip_accents": null,
76
+ "tokenize_chinese_chars": true,
77
+ "tokenizer_class": "LayoutLMv2Tokenizer",
78
+ "unk_token": "[UNK]"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d76a248d61f46f4b3f56301d756658a571ec584eadccee7e3cc826cfc1ad11
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff