Training in progress, step 200
Browse files- config.json +209 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- runs/Feb11_08-54-29_04e5fe0d3103/events.out.tfevents.1707644407.04e5fe0d3103.33992.0 +3 -0
- runs/Feb11_09-42-15_04e5fe0d3103/events.out.tfevents.1707644537.04e5fe0d3103.33992.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dandelin/vilt-b32-mlm",
|
3 |
+
"architectures": [
|
4 |
+
"ViltForQuestionAnswering"
|
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": "out",
|
12 |
+
"1": "girl",
|
13 |
+
"2": "white and black",
|
14 |
+
"3": "shadows",
|
15 |
+
"4": "double",
|
16 |
+
"5": "wine tasting",
|
17 |
+
"6": "queen",
|
18 |
+
"7": "not sure",
|
19 |
+
"8": "10",
|
20 |
+
"9": "many",
|
21 |
+
"10": "tired",
|
22 |
+
"11": "cat",
|
23 |
+
"12": "woman",
|
24 |
+
"13": "park",
|
25 |
+
"14": "suv",
|
26 |
+
"15": "wine",
|
27 |
+
"16": "jeep",
|
28 |
+
"17": "hat",
|
29 |
+
"18": "red and yellow",
|
30 |
+
"19": "red and blue",
|
31 |
+
"20": "1",
|
32 |
+
"21": "at table",
|
33 |
+
"22": "6",
|
34 |
+
"23": "no",
|
35 |
+
"24": "sky",
|
36 |
+
"25": "brown",
|
37 |
+
"26": "hawaii",
|
38 |
+
"27": "table",
|
39 |
+
"28": "plastic",
|
40 |
+
"29": "cup",
|
41 |
+
"30": "birthday",
|
42 |
+
"31": "donut",
|
43 |
+
"32": "crossing",
|
44 |
+
"33": "down",
|
45 |
+
"34": "skateboard",
|
46 |
+
"35": "3",
|
47 |
+
"36": "full",
|
48 |
+
"37": "gray",
|
49 |
+
"38": "style",
|
50 |
+
"39": "bedroom",
|
51 |
+
"40": "8",
|
52 |
+
"41": "little girl",
|
53 |
+
"42": "pink",
|
54 |
+
"43": "2",
|
55 |
+
"44": "sun",
|
56 |
+
"45": "boy",
|
57 |
+
"46": "red",
|
58 |
+
"47": "shadow",
|
59 |
+
"48": "wedding",
|
60 |
+
"49": "shrimp",
|
61 |
+
"50": "dog",
|
62 |
+
"51": "crown",
|
63 |
+
"52": "king",
|
64 |
+
"53": "bus",
|
65 |
+
"54": "0",
|
66 |
+
"55": "blue and white",
|
67 |
+
"56": "wall",
|
68 |
+
"57": "4",
|
69 |
+
"58": "5",
|
70 |
+
"59": "7",
|
71 |
+
"60": "black",
|
72 |
+
"61": "chair",
|
73 |
+
"62": "yellow",
|
74 |
+
"63": "car",
|
75 |
+
"64": "train",
|
76 |
+
"65": "fashion",
|
77 |
+
"66": "resting",
|
78 |
+
"67": "walking",
|
79 |
+
"68": "woods",
|
80 |
+
"69": "they aren't",
|
81 |
+
"70": "backpack",
|
82 |
+
"71": "chopsticks",
|
83 |
+
"72": "forest",
|
84 |
+
"73": "leather",
|
85 |
+
"74": "white and blue",
|
86 |
+
"75": "picnic table",
|
87 |
+
"76": "ice cream",
|
88 |
+
"77": "blonde",
|
89 |
+
"78": "human",
|
90 |
+
"79": "beige",
|
91 |
+
"80": "green",
|
92 |
+
"81": "air",
|
93 |
+
"82": "doughnut",
|
94 |
+
"83": "yes",
|
95 |
+
"84": "right",
|
96 |
+
"85": "watching",
|
97 |
+
"86": "outside",
|
98 |
+
"87": "white"
|
99 |
+
},
|
100 |
+
"image_size": 384,
|
101 |
+
"initializer_range": 0.02,
|
102 |
+
"intermediate_size": 3072,
|
103 |
+
"label2id": {
|
104 |
+
"0": 54,
|
105 |
+
"1": 20,
|
106 |
+
"10": 8,
|
107 |
+
"2": 43,
|
108 |
+
"3": 35,
|
109 |
+
"4": 57,
|
110 |
+
"5": 58,
|
111 |
+
"6": 22,
|
112 |
+
"7": 59,
|
113 |
+
"8": 40,
|
114 |
+
"air": 81,
|
115 |
+
"at table": 21,
|
116 |
+
"backpack": 70,
|
117 |
+
"bedroom": 39,
|
118 |
+
"beige": 79,
|
119 |
+
"birthday": 30,
|
120 |
+
"black": 60,
|
121 |
+
"blonde": 77,
|
122 |
+
"blue and white": 55,
|
123 |
+
"boy": 45,
|
124 |
+
"brown": 25,
|
125 |
+
"bus": 53,
|
126 |
+
"car": 63,
|
127 |
+
"cat": 11,
|
128 |
+
"chair": 61,
|
129 |
+
"chopsticks": 71,
|
130 |
+
"crossing": 32,
|
131 |
+
"crown": 51,
|
132 |
+
"cup": 29,
|
133 |
+
"dog": 50,
|
134 |
+
"donut": 31,
|
135 |
+
"double": 4,
|
136 |
+
"doughnut": 82,
|
137 |
+
"down": 33,
|
138 |
+
"fashion": 65,
|
139 |
+
"forest": 72,
|
140 |
+
"full": 36,
|
141 |
+
"girl": 1,
|
142 |
+
"gray": 37,
|
143 |
+
"green": 80,
|
144 |
+
"hat": 17,
|
145 |
+
"hawaii": 26,
|
146 |
+
"human": 78,
|
147 |
+
"ice cream": 76,
|
148 |
+
"jeep": 16,
|
149 |
+
"king": 52,
|
150 |
+
"leather": 73,
|
151 |
+
"little girl": 41,
|
152 |
+
"many": 9,
|
153 |
+
"no": 23,
|
154 |
+
"not sure": 7,
|
155 |
+
"out": 0,
|
156 |
+
"outside": 86,
|
157 |
+
"park": 13,
|
158 |
+
"picnic table": 75,
|
159 |
+
"pink": 42,
|
160 |
+
"plastic": 28,
|
161 |
+
"queen": 6,
|
162 |
+
"red": 46,
|
163 |
+
"red and blue": 19,
|
164 |
+
"red and yellow": 18,
|
165 |
+
"resting": 66,
|
166 |
+
"right": 84,
|
167 |
+
"shadow": 47,
|
168 |
+
"shadows": 3,
|
169 |
+
"shrimp": 49,
|
170 |
+
"skateboard": 34,
|
171 |
+
"sky": 24,
|
172 |
+
"style": 38,
|
173 |
+
"sun": 44,
|
174 |
+
"suv": 14,
|
175 |
+
"table": 27,
|
176 |
+
"they aren't": 69,
|
177 |
+
"tired": 10,
|
178 |
+
"train": 64,
|
179 |
+
"walking": 67,
|
180 |
+
"wall": 56,
|
181 |
+
"watching": 85,
|
182 |
+
"wedding": 48,
|
183 |
+
"white": 87,
|
184 |
+
"white and black": 2,
|
185 |
+
"white and blue": 74,
|
186 |
+
"wine": 15,
|
187 |
+
"wine tasting": 5,
|
188 |
+
"woman": 12,
|
189 |
+
"woods": 68,
|
190 |
+
"yellow": 62,
|
191 |
+
"yes": 83
|
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": "4.37.2",
|
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:f3f216e4c1ee0e1aed16b466b8e2d18e081d1a0a610b127a77992efcc5390b21
|
3 |
+
size 451682896
|
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/Feb11_08-54-29_04e5fe0d3103/events.out.tfevents.1707644407.04e5fe0d3103.33992.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf55ab9e4e6f168eda286605e9f205ee9f627c0fa9802a0a74170bb5e8bce44f
|
3 |
+
size 7726
|
runs/Feb11_09-42-15_04e5fe0d3103/events.out.tfevents.1707644537.04e5fe0d3103.33992.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae6002b0923e059191b72b25479dcf3054abf662b1f153b09a4c54eb788e0a93
|
3 |
+
size 8348
|
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": true,
|
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 sha256:1ded41bc237a4789c526078cf745092d0e84a58c79705ac848c4e55619a357c6
|
3 |
+
size 4728
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|