Training in progress, step 500
Browse files- config.json +0 -184
- pytorch_model.bin +1 -1
- tokenizer.json +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -24,190 +24,6 @@
|
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
27 |
-
"task_specific_params": {
|
28 |
-
"langid_map": {
|
29 |
-
"amharic": [
|
30 |
-
35,
|
31 |
-
"\u2581<extra_id_64>"
|
32 |
-
],
|
33 |
-
"arabic": [
|
34 |
-
4,
|
35 |
-
"\u2581<extra_id_95>"
|
36 |
-
],
|
37 |
-
"azerbaijani": [
|
38 |
-
7,
|
39 |
-
"\u2581<extra_id_92>"
|
40 |
-
],
|
41 |
-
"bengali": [
|
42 |
-
42,
|
43 |
-
"\u2581<extra_id_57>"
|
44 |
-
],
|
45 |
-
"burmese": [
|
46 |
-
33,
|
47 |
-
"\u2581<extra_id_66>"
|
48 |
-
],
|
49 |
-
"chinese_simplified": [
|
50 |
-
40,
|
51 |
-
"\u2581<extra_id_59>"
|
52 |
-
],
|
53 |
-
"chinese_traditional": [
|
54 |
-
44,
|
55 |
-
"\u2581<extra_id_55>"
|
56 |
-
],
|
57 |
-
"english": [
|
58 |
-
30,
|
59 |
-
"\u2581<extra_id_69>"
|
60 |
-
],
|
61 |
-
"french": [
|
62 |
-
10,
|
63 |
-
"\u2581<extra_id_89>"
|
64 |
-
],
|
65 |
-
"gujarati": [
|
66 |
-
27,
|
67 |
-
"\u2581<extra_id_72>"
|
68 |
-
],
|
69 |
-
"hausa": [
|
70 |
-
43,
|
71 |
-
"\u2581<extra_id_56>"
|
72 |
-
],
|
73 |
-
"hindi": [
|
74 |
-
21,
|
75 |
-
"\u2581<extra_id_78>"
|
76 |
-
],
|
77 |
-
"igbo": [
|
78 |
-
9,
|
79 |
-
"\u2581<extra_id_90>"
|
80 |
-
],
|
81 |
-
"indonesian": [
|
82 |
-
1,
|
83 |
-
"\u2581<extra_id_98>"
|
84 |
-
],
|
85 |
-
"japanese": [
|
86 |
-
37,
|
87 |
-
"\u2581<extra_id_62>"
|
88 |
-
],
|
89 |
-
"kirundi": [
|
90 |
-
0,
|
91 |
-
"\u2581<extra_id_99>"
|
92 |
-
],
|
93 |
-
"korean": [
|
94 |
-
29,
|
95 |
-
"\u2581<extra_id_70>"
|
96 |
-
],
|
97 |
-
"kyrgyz": [
|
98 |
-
5,
|
99 |
-
"\u2581<extra_id_94>"
|
100 |
-
],
|
101 |
-
"marathi": [
|
102 |
-
13,
|
103 |
-
"\u2581<extra_id_86>"
|
104 |
-
],
|
105 |
-
"nepali": [
|
106 |
-
20,
|
107 |
-
"\u2581<extra_id_79>"
|
108 |
-
],
|
109 |
-
"oromo": [
|
110 |
-
41,
|
111 |
-
"\u2581<extra_id_58>"
|
112 |
-
],
|
113 |
-
"pashto": [
|
114 |
-
34,
|
115 |
-
"\u2581<extra_id_65>"
|
116 |
-
],
|
117 |
-
"persian": [
|
118 |
-
23,
|
119 |
-
"\u2581<extra_id_76>"
|
120 |
-
],
|
121 |
-
"pidgin": [
|
122 |
-
14,
|
123 |
-
"\u2581<extra_id_85>"
|
124 |
-
],
|
125 |
-
"portuguese": [
|
126 |
-
39,
|
127 |
-
"\u2581<extra_id_60>"
|
128 |
-
],
|
129 |
-
"punjabi": [
|
130 |
-
17,
|
131 |
-
"\u2581<extra_id_82>"
|
132 |
-
],
|
133 |
-
"russian": [
|
134 |
-
36,
|
135 |
-
"\u2581<extra_id_63>"
|
136 |
-
],
|
137 |
-
"scottish_gaelic": [
|
138 |
-
24,
|
139 |
-
"\u2581<extra_id_75>"
|
140 |
-
],
|
141 |
-
"serbian_cyrillic": [
|
142 |
-
28,
|
143 |
-
"\u2581<extra_id_71>"
|
144 |
-
],
|
145 |
-
"serbian_latin": [
|
146 |
-
11,
|
147 |
-
"\u2581<extra_id_88>"
|
148 |
-
],
|
149 |
-
"sinhala": [
|
150 |
-
31,
|
151 |
-
"\u2581<extra_id_68>"
|
152 |
-
],
|
153 |
-
"somali": [
|
154 |
-
19,
|
155 |
-
"\u2581<extra_id_80>"
|
156 |
-
],
|
157 |
-
"spanish": [
|
158 |
-
3,
|
159 |
-
"\u2581<extra_id_96>"
|
160 |
-
],
|
161 |
-
"swahili": [
|
162 |
-
18,
|
163 |
-
"\u2581<extra_id_81>"
|
164 |
-
],
|
165 |
-
"tamil": [
|
166 |
-
32,
|
167 |
-
"\u2581<extra_id_67>"
|
168 |
-
],
|
169 |
-
"telugu": [
|
170 |
-
22,
|
171 |
-
"\u2581<extra_id_77>"
|
172 |
-
],
|
173 |
-
"thai": [
|
174 |
-
6,
|
175 |
-
"\u2581<extra_id_93>"
|
176 |
-
],
|
177 |
-
"tigrinya": [
|
178 |
-
16,
|
179 |
-
"\u2581<extra_id_83>"
|
180 |
-
],
|
181 |
-
"turkish": [
|
182 |
-
15,
|
183 |
-
"\u2581<extra_id_84>"
|
184 |
-
],
|
185 |
-
"ukrainian": [
|
186 |
-
2,
|
187 |
-
"\u2581<extra_id_97>"
|
188 |
-
],
|
189 |
-
"urdu": [
|
190 |
-
38,
|
191 |
-
"\u2581<extra_id_61>"
|
192 |
-
],
|
193 |
-
"uzbek": [
|
194 |
-
8,
|
195 |
-
"\u2581<extra_id_91>"
|
196 |
-
],
|
197 |
-
"vietnamese": [
|
198 |
-
12,
|
199 |
-
"\u2581<extra_id_87>"
|
200 |
-
],
|
201 |
-
"welsh": [
|
202 |
-
26,
|
203 |
-
"\u2581<extra_id_73>"
|
204 |
-
],
|
205 |
-
"yoruba": [
|
206 |
-
25,
|
207 |
-
"\u2581<extra_id_74>"
|
208 |
-
]
|
209 |
-
}
|
210 |
-
},
|
211 |
"tokenizer_class": "T5Tokenizer",
|
212 |
"torch_dtype": "float32",
|
213 |
"transformers_version": "4.33.0",
|
|
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"tokenizer_class": "T5Tokenizer",
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.33.0",
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1200772613
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55446231712011f0ae2a5454a2e07cff9c68ca8ce1e5b170e5617da5a48db4c4
|
3 |
size 1200772613
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16330467
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c16a691e78a3acdc36051bafeda04b83c7390133f16c34a08660f4d2dde72df3
|
3 |
size 16330467
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26d8be03eb5447c510d2efea50db0842451b4326788839e013ca69f3ca91504d
|
3 |
size 4219
|