hugo-albert
commited on
Commit
•
897e7e3
1
Parent(s):
df34f62
Training in progress epoch 0
Browse files- config.json +130 -130
- merges.txt +0 -0
- model.safetensors +1 -1
- special_tokens_map.json +25 -11
- tokenizer.json +0 -0
- tokenizer_config.json +26 -25
- vocab.json +0 -0
config.json
CHANGED
@@ -12,142 +12,142 @@
|
|
12 |
"hidden_dropout_prob": 0.0,
|
13 |
"hidden_size": 1024,
|
14 |
"id2label": {
|
15 |
-
"0": "
|
16 |
-
"1": "
|
17 |
-
"2": "
|
18 |
-
"3": "
|
19 |
-
"4": "
|
20 |
-
"5": "
|
21 |
-
"6": "
|
22 |
-
"7": "
|
23 |
-
"8": "
|
24 |
-
"9": "
|
25 |
-
"10": "
|
26 |
-
"11": "
|
27 |
-
"12": "
|
28 |
"13": "vam",
|
29 |
-
"14": "
|
30 |
-
"15": "
|
31 |
-
"16": "
|
32 |
-
"17": "
|
33 |
-
"18": "
|
34 |
-
"19": "
|
35 |
-
"20": "
|
36 |
-
"21": "
|
37 |
-
"22": "
|
38 |
-
"23": "
|
39 |
-
"24": "
|
40 |
-
"25": "
|
41 |
-
"26": "
|
42 |
-
"27": "
|
43 |
-
"28": "
|
44 |
-
"29": "
|
45 |
-
"30": "
|
46 |
-
"31": "
|
47 |
-
"32": "
|
48 |
-
"33": "
|
49 |
-
"34": "
|
50 |
-
"35": "
|
51 |
-
"36": "
|
52 |
-
"37": "
|
53 |
-
"38": "
|
54 |
-
"39": "
|
55 |
-
"40": "
|
56 |
-
"41": "
|
57 |
-
"42": "
|
58 |
-
"43": "
|
59 |
-
"44": "
|
60 |
-
"45": "
|
61 |
-
"46": "
|
62 |
-
"47": "
|
63 |
-
"48": "
|
64 |
-
"49": "
|
65 |
-
"50": "
|
66 |
-
"51": "
|
67 |
-
"52": "
|
68 |
-
"53": "
|
69 |
-
"54": "
|
70 |
-
"55": "
|
71 |
-
"56": "
|
72 |
-
"57": "
|
73 |
-
"58": "
|
74 |
-
"59": "
|
75 |
-
"60": "
|
76 |
-
"61": "
|
77 |
-
"62": "
|
78 |
-
"63": "
|
79 |
-
"64": "
|
80 |
-
"65": "
|
81 |
},
|
82 |
"initializer_range": 0.02,
|
83 |
"intermediate_size": 4096,
|
84 |
"label2id": {
|
85 |
-
"Faa":
|
86 |
-
"Fat":
|
87 |
-
"Fc":
|
88 |
-
"Fd":
|
89 |
-
"Fe":
|
90 |
-
"Fg":
|
91 |
-
"Fh":
|
92 |
-
"Fia":
|
93 |
-
"Fit":
|
94 |
-
"Fp":
|
95 |
-
"Fpa":
|
96 |
-
"Fpt":
|
97 |
-
"Fs":
|
98 |
-
"Fx":
|
99 |
-
"Fz":
|
100 |
-
"I":
|
101 |
-
"W":
|
102 |
-
"X":
|
103 |
-
"Y":
|
104 |
-
"Z":
|
105 |
-
"Zm":
|
106 |
-
"Zp":
|
107 |
-
"ao":
|
108 |
-
"aq":
|
109 |
-
"cc":
|
110 |
-
"cs":
|
111 |
-
"da":
|
112 |
-
"dd":
|
113 |
-
"de":
|
114 |
-
"di":
|
115 |
-
"dn":
|
116 |
-
"dp":
|
117 |
-
"dt":
|
118 |
-
"i":
|
119 |
-
"nc":
|
120 |
-
"np":
|
121 |
-
"p0":
|
122 |
-
"pd":
|
123 |
-
"pe":
|
124 |
-
"pi":
|
125 |
-
"pn":
|
126 |
-
"pp":
|
127 |
-
"pr":
|
128 |
-
"pt":
|
129 |
-
"px":
|
130 |
-
"rg":
|
131 |
-
"rn":
|
132 |
-
"sp":
|
133 |
-
"vag":
|
134 |
-
"vai":
|
135 |
"vam": 13,
|
136 |
-
"van":
|
137 |
-
"vap":
|
138 |
-
"vas":
|
139 |
-
"vmg":
|
140 |
-
"vmi":
|
141 |
-
"vmm":
|
142 |
-
"vmn":
|
143 |
-
"vmp":
|
144 |
-
"vms":
|
145 |
-
"vsg":
|
146 |
-
"vsi":
|
147 |
-
"vsm":
|
148 |
-
"vsn":
|
149 |
-
"vsp":
|
150 |
-
"vss":
|
151 |
},
|
152 |
"layer_norm_eps": 1e-05,
|
153 |
"max_position_embeddings": 514,
|
|
|
12 |
"hidden_dropout_prob": 0.0,
|
13 |
"hidden_size": 1024,
|
14 |
"id2label": {
|
15 |
+
"0": "X",
|
16 |
+
"1": "vai",
|
17 |
+
"2": "vap",
|
18 |
+
"3": "Zm",
|
19 |
+
"4": "vas",
|
20 |
+
"5": "Fat",
|
21 |
+
"6": "Fp",
|
22 |
+
"7": "ao",
|
23 |
+
"8": "W",
|
24 |
+
"9": "Fg",
|
25 |
+
"10": "sp",
|
26 |
+
"11": "vsg",
|
27 |
+
"12": "dt",
|
28 |
"13": "vam",
|
29 |
+
"14": "pi",
|
30 |
+
"15": "dp",
|
31 |
+
"16": "vmm",
|
32 |
+
"17": "pn",
|
33 |
+
"18": "vmg",
|
34 |
+
"19": "Fpt",
|
35 |
+
"20": "rg",
|
36 |
+
"21": "Fs",
|
37 |
+
"22": "i",
|
38 |
+
"23": "Zp",
|
39 |
+
"24": "aq",
|
40 |
+
"25": "Fd",
|
41 |
+
"26": "vms",
|
42 |
+
"27": "vmp",
|
43 |
+
"28": "Fz",
|
44 |
+
"29": "dn",
|
45 |
+
"30": "vag",
|
46 |
+
"31": "vsn",
|
47 |
+
"32": "nc",
|
48 |
+
"33": "vss",
|
49 |
+
"34": "vsm",
|
50 |
+
"35": "Fh",
|
51 |
+
"36": "I",
|
52 |
+
"37": "de",
|
53 |
+
"38": "px",
|
54 |
+
"39": "Fc",
|
55 |
+
"40": "Faa",
|
56 |
+
"41": "pe",
|
57 |
+
"42": "Z",
|
58 |
+
"43": "vmi",
|
59 |
+
"44": "pp",
|
60 |
+
"45": "da",
|
61 |
+
"46": "cs",
|
62 |
+
"47": "rn",
|
63 |
+
"48": "vsi",
|
64 |
+
"49": "Fit",
|
65 |
+
"50": "Fe",
|
66 |
+
"51": "p0",
|
67 |
+
"52": "Fx",
|
68 |
+
"53": "Y",
|
69 |
+
"54": "cc",
|
70 |
+
"55": "van",
|
71 |
+
"56": "Fpa",
|
72 |
+
"57": "pr",
|
73 |
+
"58": "dd",
|
74 |
+
"59": "pt",
|
75 |
+
"60": "vmn",
|
76 |
+
"61": "di",
|
77 |
+
"62": "np",
|
78 |
+
"63": "vsp",
|
79 |
+
"64": "Fia",
|
80 |
+
"65": "pd"
|
81 |
},
|
82 |
"initializer_range": 0.02,
|
83 |
"intermediate_size": 4096,
|
84 |
"label2id": {
|
85 |
+
"Faa": 40,
|
86 |
+
"Fat": 5,
|
87 |
+
"Fc": 39,
|
88 |
+
"Fd": 25,
|
89 |
+
"Fe": 50,
|
90 |
+
"Fg": 9,
|
91 |
+
"Fh": 35,
|
92 |
+
"Fia": 64,
|
93 |
+
"Fit": 49,
|
94 |
+
"Fp": 6,
|
95 |
+
"Fpa": 56,
|
96 |
+
"Fpt": 19,
|
97 |
+
"Fs": 21,
|
98 |
+
"Fx": 52,
|
99 |
+
"Fz": 28,
|
100 |
+
"I": 36,
|
101 |
+
"W": 8,
|
102 |
+
"X": 0,
|
103 |
+
"Y": 53,
|
104 |
+
"Z": 42,
|
105 |
+
"Zm": 3,
|
106 |
+
"Zp": 23,
|
107 |
+
"ao": 7,
|
108 |
+
"aq": 24,
|
109 |
+
"cc": 54,
|
110 |
+
"cs": 46,
|
111 |
+
"da": 45,
|
112 |
+
"dd": 58,
|
113 |
+
"de": 37,
|
114 |
+
"di": 61,
|
115 |
+
"dn": 29,
|
116 |
+
"dp": 15,
|
117 |
+
"dt": 12,
|
118 |
+
"i": 22,
|
119 |
+
"nc": 32,
|
120 |
+
"np": 62,
|
121 |
+
"p0": 51,
|
122 |
+
"pd": 65,
|
123 |
+
"pe": 41,
|
124 |
+
"pi": 14,
|
125 |
+
"pn": 17,
|
126 |
+
"pp": 44,
|
127 |
+
"pr": 57,
|
128 |
+
"pt": 59,
|
129 |
+
"px": 38,
|
130 |
+
"rg": 20,
|
131 |
+
"rn": 47,
|
132 |
+
"sp": 10,
|
133 |
+
"vag": 30,
|
134 |
+
"vai": 1,
|
135 |
"vam": 13,
|
136 |
+
"van": 55,
|
137 |
+
"vap": 2,
|
138 |
+
"vas": 4,
|
139 |
+
"vmg": 18,
|
140 |
+
"vmi": 43,
|
141 |
+
"vmm": 16,
|
142 |
+
"vmn": 60,
|
143 |
+
"vmp": 27,
|
144 |
+
"vms": 26,
|
145 |
+
"vsg": 11,
|
146 |
+
"vsi": 48,
|
147 |
+
"vsm": 34,
|
148 |
+
"vsn": 31,
|
149 |
+
"vsp": 63,
|
150 |
+
"vss": 33
|
151 |
},
|
152 |
"layer_norm_eps": 1e-05,
|
153 |
"max_position_embeddings": 514,
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1417546912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc4b917fde90db6334cb3c9da523e6c0ebd33e7b8744a79c1de5d5c5cac953e2
|
3 |
size 1417546912
|
special_tokens_map.json
CHANGED
@@ -1,36 +1,50 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
-
"normalized":
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
-
"normalized":
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"sep_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
-
"normalized":
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
"unk_token": {
|
31 |
-
"content": "
|
32 |
"lstrip": false,
|
33 |
-
"normalized":
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
}
|
|
|
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 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,57 +1,58 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
-
"normalized":
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
-
"lstrip":
|
38 |
-
"normalized":
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"cls_token": "
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"mask_token": "
|
|
|
49 |
"model_max_length": 512,
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"tokenizer_class": "BertTokenizer",
|
56 |
-
"unk_token": "[UNK]"
|
57 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": true,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
+
"content": "<s>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
}
|
44 |
},
|
45 |
+
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
|
|
|
|
58 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|