Training in progress, epoch 1
Browse files- added_tokens.json +6 -0
- config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +65 -1
- tokenizer_config.json +48 -0
- training_args.bin +2 -2
added_tokens.json
CHANGED
@@ -1,5 +1,11 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"</tsum>": 50271,
|
|
|
|
|
|
|
3 |
"<mask_s>": 50266,
|
4 |
"<mask_sg>": 50267,
|
5 |
"<sentence>": 50268,
|
|
|
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,
|
11 |
"<sentence>": 50268,
|
config.json
CHANGED
@@ -48,7 +48,7 @@
|
|
48 |
"num_hidden_layers": 6,
|
49 |
"pad_token_id": 1,
|
50 |
"torch_dtype": "float32",
|
51 |
-
"transformers_version": "4.
|
52 |
"use_cache": true,
|
53 |
-
"vocab_size":
|
54 |
}
|
|
|
48 |
"num_hidden_layers": 6,
|
49 |
"pad_token_id": 1,
|
50 |
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.40.1",
|
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 sha256:55e95e8249de4f573677f7b33c44876bc64581344bc926344ccaffeae2d68f0c
|
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,
|
@@ -115,6 +124,60 @@
|
|
115 |
"rstrip": false,
|
116 |
"normalized": false,
|
117 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
}
|
119 |
],
|
120 |
"normalizer": null,
|
@@ -151,6 +214,7 @@
|
|
151 |
"end_of_word_suffix": "",
|
152 |
"fuse_unk": false,
|
153 |
"byte_fallback": false,
|
|
|
154 |
"vocab": {
|
155 |
"<s>": 0,
|
156 |
"<pad>": 1,
|
|
|
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,
|
|
|
124 |
"rstrip": false,
|
125 |
"normalized": false,
|
126 |
"special": true
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"id": 50272,
|
130 |
+
"content": "<lsum>",
|
131 |
+
"single_word": false,
|
132 |
+
"lstrip": false,
|
133 |
+
"rstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"special": true
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"id": 50273,
|
139 |
+
"content": "</lsum>",
|
140 |
+
"single_word": false,
|
141 |
+
"lstrip": false,
|
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,
|
|
|
214 |
"end_of_word_suffix": "",
|
215 |
"fuse_unk": false,
|
216 |
"byte_fallback": false,
|
217 |
+
"ignore_merges": false,
|
218 |
"vocab": {
|
219 |
"<s>": 0,
|
220 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
@@ -96,6 +96,54 @@
|
|
96 |
"rstrip": false,
|
97 |
"single_word": false,
|
98 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
}
|
100 |
},
|
101 |
"additional_special_tokens": [
|
|
|
96 |
"rstrip": false,
|
97 |
"single_word": false,
|
98 |
"special": true
|
99 |
+
},
|
100 |
+
"50272": {
|
101 |
+
"content": "<lsum>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"50273": {
|
109 |
+
"content": "</lsum>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0817b276cad03e7066377612770e014a5d07a4c1a3b6771482351c6afaa34b6
|
3 |
+
size 5240
|