Training in progress, epoch 1
Browse files- added_tokens.json +4 -0
- config.json +1 -1
- model.safetensors +2 -2
- tokenizer.json +46 -1
- tokenizer_config.json +32 -0
- training_args.bin +1 -1
added_tokens.json
CHANGED
@@ -1,6 +1,10 @@
|
|
1 |
{
|
|
|
|
|
2 |
"</lsum>": 50273,
|
3 |
"</tsum>": 50271,
|
|
|
|
|
4 |
"<lsum>": 50272,
|
5 |
"<mask_s>": 50266,
|
6 |
"<mask_sg>": 50267,
|
|
|
1 |
{
|
2 |
+
"</disc>": 50277,
|
3 |
+
"</intro>": 50275,
|
4 |
"</lsum>": 50273,
|
5 |
"</tsum>": 50271,
|
6 |
+
"<disc>": 50276,
|
7 |
+
"<intro>": 50274,
|
8 |
"<lsum>": 50272,
|
9 |
"<mask_s>": 50266,
|
10 |
"<mask_sg>": 50267,
|
config.json
CHANGED
@@ -50,5 +50,5 @@
|
|
50 |
"torch_dtype": "float32",
|
51 |
"transformers_version": "4.35.2",
|
52 |
"use_cache": true,
|
53 |
-
"vocab_size":
|
54 |
}
|
|
|
50 |
"torch_dtype": "float32",
|
51 |
"transformers_version": "4.35.2",
|
52 |
"use_cache": true,
|
53 |
+
"vocab_size": 50278
|
54 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61e003a28d632e4e17d87a47126d91afdb8936832f1107745e0e94dd31653ee1
|
3 |
+
size 647654104
|
tokenizer.json
CHANGED
@@ -6,7 +6,16 @@
|
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 0,
|
@@ -133,6 +142,42 @@
|
|
133 |
"rstrip": false,
|
134 |
"normalized": false,
|
135 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"normalizer": null,
|
|
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 1024
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": 8,
|
15 |
+
"pad_id": 1,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
142 |
"rstrip": false,
|
143 |
"normalized": false,
|
144 |
"special": true
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"id": 50274,
|
148 |
+
"content": "<intro>",
|
149 |
+
"single_word": false,
|
150 |
+
"lstrip": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"id": 50275,
|
157 |
+
"content": "</intro>",
|
158 |
+
"single_word": false,
|
159 |
+
"lstrip": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"id": 50276,
|
166 |
+
"content": "<disc>",
|
167 |
+
"single_word": false,
|
168 |
+
"lstrip": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"normalized": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"id": 50277,
|
175 |
+
"content": "</disc>",
|
176 |
+
"single_word": false,
|
177 |
+
"lstrip": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"normalized": false,
|
180 |
+
"special": true
|
181 |
}
|
182 |
],
|
183 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -112,6 +112,38 @@
|
|
112 |
"rstrip": false,
|
113 |
"single_word": false,
|
114 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
}
|
116 |
},
|
117 |
"additional_special_tokens": [
|
|
|
112 |
"rstrip": false,
|
113 |
"single_word": false,
|
114 |
"special": true
|
115 |
+
},
|
116 |
+
"50274": {
|
117 |
+
"content": "<intro>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"50275": {
|
125 |
+
"content": "</intro>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"50276": {
|
133 |
+
"content": "<disc>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"50277": {
|
141 |
+
"content": "</disc>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
}
|
148 |
},
|
149 |
"additional_special_tokens": [
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4347
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a425402a57a3751faf0c5bc570eb7e660a92aac08ede317175abe20142412302
|
3 |
size 4347
|