Hugging Face's logo

mpillar
/
vilt_finetuned_200

TensorBoard
Safetensors
vilt
Model card Files
xet
Metrics Community
mpillar commited on
Commit
0d3af14
·
verified ·
1 Parent(s): aa5fe76

Training in progress, step 200

Browse files
Files changed (9) hide show
  1. config.json +209 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +24 -0
  4. runs/Dec02_07-07-52_cb58d764cbcf/events.out.tfevents.1733123567.cb58d764cbcf.406.0 +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +56 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dandelin/vilt-b32-mlm",
3
+ "architectures": [
4
+ "ViltSNNForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "4",
12
+ "1": "walking",
13
+ "2": "shadows",
14
+ "3": "6",
15
+ "4": "not sure",
16
+ "5": "out",
17
+ "6": "crown",
18
+ "7": "brown",
19
+ "8": "car",
20
+ "9": "hawaii",
21
+ "10": "donut",
22
+ "11": "they aren't",
23
+ "12": "7",
24
+ "13": "many",
25
+ "14": "at table",
26
+ "15": "shrimp",
27
+ "16": "air",
28
+ "17": "leather",
29
+ "18": "yellow",
30
+ "19": "wedding",
31
+ "20": "8",
32
+ "21": "black",
33
+ "22": "watching",
34
+ "23": "hat",
35
+ "24": "tired",
36
+ "25": "train",
37
+ "26": "2",
38
+ "27": "1",
39
+ "28": "human",
40
+ "29": "0",
41
+ "30": "skateboard",
42
+ "31": "no",
43
+ "32": "3",
44
+ "33": "cup",
45
+ "34": "forest",
46
+ "35": "picnic table",
47
+ "36": "boy",
48
+ "37": "woman",
49
+ "38": "blue and white",
50
+ "39": "right",
51
+ "40": "outside",
52
+ "41": "chair",
53
+ "42": "suv",
54
+ "43": "wine",
55
+ "44": "yes",
56
+ "45": "red and yellow",
57
+ "46": "jeep",
58
+ "47": "white",
59
+ "48": "backpack",
60
+ "49": "fashion",
61
+ "50": "red and blue",
62
+ "51": "bedroom",
63
+ "52": "table",
64
+ "53": "park",
65
+ "54": "full",
66
+ "55": "gray",
67
+ "56": "sky",
68
+ "57": "beige",
69
+ "58": "sun",
70
+ "59": "doughnut",
71
+ "60": "plastic",
72
+ "61": "king",
73
+ "62": "shadow",
74
+ "63": "wall",
75
+ "64": "crossing",
76
+ "65": "girl",
77
+ "66": "double",
78
+ "67": "5",
79
+ "68": "red",
80
+ "69": "pink",
81
+ "70": "bus",
82
+ "71": "wine tasting",
83
+ "72": "ice cream",
84
+ "73": "dog",
85
+ "74": "little girl",
86
+ "75": "white and black",
87
+ "76": "birthday",
88
+ "77": "down",
89
+ "78": "resting",
90
+ "79": "cat",
91
+ "80": "chopsticks",
92
+ "81": "blonde",
93
+ "82": "green",
94
+ "83": "style",
95
+ "84": "queen",
96
+ "85": "woods",
97
+ "86": "white and blue",
98
+ "87": "10"
99
+ },
100
+ "image_size": 384,
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 3072,
103
+ "label2id": {
104
+ "0": 29,
105
+ "1": 27,
106
+ "10": 87,
107
+ "2": 26,
108
+ "3": 32,
109
+ "4": 0,
110
+ "5": 67,
111
+ "6": 3,
112
+ "7": 12,
113
+ "8": 20,
114
+ "air": 16,
115
+ "at table": 14,
116
+ "backpack": 48,
117
+ "bedroom": 51,
118
+ "beige": 57,
119
+ "birthday": 76,
120
+ "black": 21,
121
+ "blonde": 81,
122
+ "blue and white": 38,
123
+ "boy": 36,
124
+ "brown": 7,
125
+ "bus": 70,
126
+ "car": 8,
127
+ "cat": 79,
128
+ "chair": 41,
129
+ "chopsticks": 80,
130
+ "crossing": 64,
131
+ "crown": 6,
132
+ "cup": 33,
133
+ "dog": 73,
134
+ "donut": 10,
135
+ "double": 66,
136
+ "doughnut": 59,
137
+ "down": 77,
138
+ "fashion": 49,
139
+ "forest": 34,
140
+ "full": 54,
141
+ "girl": 65,
142
+ "gray": 55,
143
+ "green": 82,
144
+ "hat": 23,
145
+ "hawaii": 9,
146
+ "human": 28,
147
+ "ice cream": 72,
148
+ "jeep": 46,
149
+ "king": 61,
150
+ "leather": 17,
151
+ "little girl": 74,
152
+ "many": 13,
153
+ "no": 31,
154
+ "not sure": 4,
155
+ "out": 5,
156
+ "outside": 40,
157
+ "park": 53,
158
+ "picnic table": 35,
159
+ "pink": 69,
160
+ "plastic": 60,
161
+ "queen": 84,
162
+ "red": 68,
163
+ "red and blue": 50,
164
+ "red and yellow": 45,
165
+ "resting": 78,
166
+ "right": 39,
167
+ "shadow": 62,
168
+ "shadows": 2,
169
+ "shrimp": 15,
170
+ "skateboard": 30,
171
+ "sky": 56,
172
+ "style": 83,
173
+ "sun": 58,
174
+ "suv": 42,
175
+ "table": 52,
176
+ "they aren't": 11,
177
+ "tired": 24,
178
+ "train": 25,
179
+ "walking": 1,
180
+ "wall": 63,
181
+ "watching": 22,
182
+ "wedding": 19,
183
+ "white": 47,
184
+ "white and black": 75,
185
+ "white and blue": 86,
186
+ "wine": 43,
187
+ "wine tasting": 71,
188
+ "woman": 37,
189
+ "woods": 85,
190
+ "yellow": 18,
191
+ "yes": 44
192
+ },
193
+ "layer_norm_eps": 1e-12,
194
+ "max_image_length": -1,
195
+ "max_position_embeddings": 40,
196
+ "modality_type_vocab_size": 2,
197
+ "model_type": "vilt",
198
+ "num_attention_heads": 12,
199
+ "num_channels": 3,
200
+ "num_hidden_layers": 12,
201
+ "num_images": -1,
202
+ "patch_size": 32,
203
+ "qkv_bias": true,
204
+ "tie_word_embeddings": false,
205
+ "torch_dtype": "float32",
206
+ "transformers_version": "4.46.2",
207
+ "type_vocab_size": 2,
208
+ "vocab_size": 30522
209
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8b1cb853aaabc49386eb975e4f9490f9eeac31610a75e42792fede1fe06a6e
3
+ size 448160500
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_pad": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViltImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "ViltProcessor",
18
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "shortest_edge": 384
22
+ },
23
+ "size_divisor": 32
24
+ }
runs/Dec02_07-07-52_cb58d764cbcf/events.out.tfevents.1733123567.cb58d764cbcf.406.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a91cbe5d3237a709b96f8cf7db034388b80e49be3ba5939f24b6bb1319e7d15
3
+ size 50120
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 40,
49
+ "pad_token": "[PAD]",
50
+ "processor_class": "ViltProcessor",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87b8e013e336bf8c4c266a90de20cd97f068a2979938f047b9ae993963ac7f8
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff