Training in progress, step 200
Browse files- config.json +209 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- runs/Dec02_18-36-43_c0c4081ce615/events.out.tfevents.1733164608.c0c4081ce615.961.0 +3 -0
- runs/Dec02_18-38-09_c0c4081ce615/events.out.tfevents.1733164693.c0c4081ce615.961.1 +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 |
+
"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": 0,
|
| 12 |
+
"1": 1,
|
| 13 |
+
"2": 2,
|
| 14 |
+
"3": 3,
|
| 15 |
+
"4": 4,
|
| 16 |
+
"5": 5,
|
| 17 |
+
"6": 6,
|
| 18 |
+
"7": 7,
|
| 19 |
+
"8": 8,
|
| 20 |
+
"9": 9,
|
| 21 |
+
"10": 10,
|
| 22 |
+
"11": 11,
|
| 23 |
+
"12": 12,
|
| 24 |
+
"13": 13,
|
| 25 |
+
"14": 14,
|
| 26 |
+
"15": 15,
|
| 27 |
+
"16": 16,
|
| 28 |
+
"17": 17,
|
| 29 |
+
"18": 18,
|
| 30 |
+
"19": 19,
|
| 31 |
+
"20": 20,
|
| 32 |
+
"21": 21,
|
| 33 |
+
"22": 22,
|
| 34 |
+
"23": 23,
|
| 35 |
+
"24": 24,
|
| 36 |
+
"25": 25,
|
| 37 |
+
"26": 26,
|
| 38 |
+
"27": 27,
|
| 39 |
+
"28": 28,
|
| 40 |
+
"29": 29,
|
| 41 |
+
"30": 30,
|
| 42 |
+
"31": 31,
|
| 43 |
+
"32": 32,
|
| 44 |
+
"33": 33,
|
| 45 |
+
"34": 34,
|
| 46 |
+
"35": 35,
|
| 47 |
+
"36": 36,
|
| 48 |
+
"37": 37,
|
| 49 |
+
"38": 38,
|
| 50 |
+
"39": 39,
|
| 51 |
+
"40": 40,
|
| 52 |
+
"41": 41,
|
| 53 |
+
"42": 42,
|
| 54 |
+
"43": 43,
|
| 55 |
+
"44": 44,
|
| 56 |
+
"45": 45,
|
| 57 |
+
"46": 46,
|
| 58 |
+
"47": 47,
|
| 59 |
+
"48": 48,
|
| 60 |
+
"49": 49,
|
| 61 |
+
"50": 50,
|
| 62 |
+
"51": 51,
|
| 63 |
+
"52": 52,
|
| 64 |
+
"53": 53,
|
| 65 |
+
"54": 54,
|
| 66 |
+
"55": 55,
|
| 67 |
+
"56": 56,
|
| 68 |
+
"57": 57,
|
| 69 |
+
"58": 58,
|
| 70 |
+
"59": 59,
|
| 71 |
+
"60": 60,
|
| 72 |
+
"61": 61,
|
| 73 |
+
"62": 62,
|
| 74 |
+
"63": 63,
|
| 75 |
+
"64": 64,
|
| 76 |
+
"65": 65,
|
| 77 |
+
"66": 66,
|
| 78 |
+
"67": 67,
|
| 79 |
+
"68": 68,
|
| 80 |
+
"69": 69,
|
| 81 |
+
"70": 70,
|
| 82 |
+
"71": 71,
|
| 83 |
+
"72": 72,
|
| 84 |
+
"73": 73,
|
| 85 |
+
"74": 74,
|
| 86 |
+
"75": 75,
|
| 87 |
+
"76": 76,
|
| 88 |
+
"77": 77,
|
| 89 |
+
"78": 78,
|
| 90 |
+
"79": 79,
|
| 91 |
+
"80": 80,
|
| 92 |
+
"81": 81,
|
| 93 |
+
"82": 82,
|
| 94 |
+
"83": 83,
|
| 95 |
+
"84": 84,
|
| 96 |
+
"85": 85,
|
| 97 |
+
"86": 86,
|
| 98 |
+
"87": 87
|
| 99 |
+
},
|
| 100 |
+
"image_size": 384,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 3072,
|
| 103 |
+
"label2id": {
|
| 104 |
+
"0": 0,
|
| 105 |
+
"1": 1,
|
| 106 |
+
"2": 2,
|
| 107 |
+
"3": 3,
|
| 108 |
+
"4": 4,
|
| 109 |
+
"5": 5,
|
| 110 |
+
"6": 6,
|
| 111 |
+
"7": 7,
|
| 112 |
+
"8": 8,
|
| 113 |
+
"9": 9,
|
| 114 |
+
"10": 10,
|
| 115 |
+
"11": 11,
|
| 116 |
+
"12": 12,
|
| 117 |
+
"13": 13,
|
| 118 |
+
"14": 14,
|
| 119 |
+
"15": 15,
|
| 120 |
+
"16": 16,
|
| 121 |
+
"17": 17,
|
| 122 |
+
"18": 18,
|
| 123 |
+
"19": 19,
|
| 124 |
+
"20": 20,
|
| 125 |
+
"21": 21,
|
| 126 |
+
"22": 22,
|
| 127 |
+
"23": 23,
|
| 128 |
+
"24": 24,
|
| 129 |
+
"25": 25,
|
| 130 |
+
"26": 26,
|
| 131 |
+
"27": 27,
|
| 132 |
+
"28": 28,
|
| 133 |
+
"29": 29,
|
| 134 |
+
"30": 30,
|
| 135 |
+
"31": 31,
|
| 136 |
+
"32": 32,
|
| 137 |
+
"33": 33,
|
| 138 |
+
"34": 34,
|
| 139 |
+
"35": 35,
|
| 140 |
+
"36": 36,
|
| 141 |
+
"37": 37,
|
| 142 |
+
"38": 38,
|
| 143 |
+
"39": 39,
|
| 144 |
+
"40": 40,
|
| 145 |
+
"41": 41,
|
| 146 |
+
"42": 42,
|
| 147 |
+
"43": 43,
|
| 148 |
+
"44": 44,
|
| 149 |
+
"45": 45,
|
| 150 |
+
"46": 46,
|
| 151 |
+
"47": 47,
|
| 152 |
+
"48": 48,
|
| 153 |
+
"49": 49,
|
| 154 |
+
"50": 50,
|
| 155 |
+
"51": 51,
|
| 156 |
+
"52": 52,
|
| 157 |
+
"53": 53,
|
| 158 |
+
"54": 54,
|
| 159 |
+
"55": 55,
|
| 160 |
+
"56": 56,
|
| 161 |
+
"57": 57,
|
| 162 |
+
"58": 58,
|
| 163 |
+
"59": 59,
|
| 164 |
+
"60": 60,
|
| 165 |
+
"61": 61,
|
| 166 |
+
"62": 62,
|
| 167 |
+
"63": 63,
|
| 168 |
+
"64": 64,
|
| 169 |
+
"65": 65,
|
| 170 |
+
"66": 66,
|
| 171 |
+
"67": 67,
|
| 172 |
+
"68": 68,
|
| 173 |
+
"69": 69,
|
| 174 |
+
"70": 70,
|
| 175 |
+
"71": 71,
|
| 176 |
+
"72": 72,
|
| 177 |
+
"73": 73,
|
| 178 |
+
"74": 74,
|
| 179 |
+
"75": 75,
|
| 180 |
+
"76": 76,
|
| 181 |
+
"77": 77,
|
| 182 |
+
"78": 78,
|
| 183 |
+
"79": 79,
|
| 184 |
+
"80": 80,
|
| 185 |
+
"81": 81,
|
| 186 |
+
"82": 82,
|
| 187 |
+
"83": 83,
|
| 188 |
+
"84": 84,
|
| 189 |
+
"85": 85,
|
| 190 |
+
"86": 86,
|
| 191 |
+
"87": 87
|
| 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 sha256:16f351b9ea26d36985fa00f8b13432ffa97ea46c1ffda24d13fc4619481c578e
|
| 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_18-36-43_c0c4081ce615/events.out.tfevents.1733164608.c0c4081ce615.961.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62a2534d26e174409561ec1a2798c096209ac817e3002f0e72d1d1d7959ff3f4
|
| 3 |
+
size 8376
|
runs/Dec02_18-38-09_c0c4081ce615/events.out.tfevents.1733164693.c0c4081ce615.961.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6f6f470ef5c1487334018cb21d0e6a2b22dc4d9d067d0ab5059ded257bad79e
|
| 3 |
+
size 49600
|
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:f9c3c39ff8bd705ae459d0f2f1e40196bd825eddb5cfd4a3acd99c2ec8172812
|
| 3 |
+
size 5240
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|