Training in progress, step 1114
Browse files- added_tokens.json +594 -0
- config.json +58 -0
- model.safetensors +3 -0
- runs/Apr27_00-02-14_ip-10-192-12-77/events.out.tfevents.1745712146.ip-10-192-12-77.2238.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ءً": 50553,
|
| 3 |
+
"ءًا": 50561,
|
| 4 |
+
"ءًّ": 50558,
|
| 5 |
+
"ءٌ": 50552,
|
| 6 |
+
"ءٌّ": 50560,
|
| 7 |
+
"ءٍ": 50551,
|
| 8 |
+
"ءٍّ": 50559,
|
| 9 |
+
"ءَ": 50546,
|
| 10 |
+
"ءَّ": 50554,
|
| 11 |
+
"ءُ": 50548,
|
| 12 |
+
"ءُّ": 50556,
|
| 13 |
+
"ءِ": 50547,
|
| 14 |
+
"ءِّ": 50555,
|
| 15 |
+
"ءّ": 50549,
|
| 16 |
+
"ءْ": 50550,
|
| 17 |
+
"ءّْ": 50557,
|
| 18 |
+
"آً": 50569,
|
| 19 |
+
"آًا": 50577,
|
| 20 |
+
"آًّ": 50574,
|
| 21 |
+
"آٌ": 50568,
|
| 22 |
+
"آٌّ": 50576,
|
| 23 |
+
"آٍ": 50567,
|
| 24 |
+
"آٍّ": 50575,
|
| 25 |
+
"آَ": 50562,
|
| 26 |
+
"آَّ": 50570,
|
| 27 |
+
"آُ": 50564,
|
| 28 |
+
"آُّ": 50572,
|
| 29 |
+
"آِ": 50563,
|
| 30 |
+
"آِّ": 50571,
|
| 31 |
+
"آّ": 50565,
|
| 32 |
+
"آْ": 50566,
|
| 33 |
+
"آّْ": 50573,
|
| 34 |
+
"أً": 50473,
|
| 35 |
+
"أًا": 50481,
|
| 36 |
+
"أًّ": 50478,
|
| 37 |
+
"أٌ": 50472,
|
| 38 |
+
"أٌّ": 50480,
|
| 39 |
+
"أٍ": 50471,
|
| 40 |
+
"أٍّ": 50479,
|
| 41 |
+
"أَ": 50466,
|
| 42 |
+
"أَّ": 50474,
|
| 43 |
+
"أُ": 50468,
|
| 44 |
+
"أُّ": 50476,
|
| 45 |
+
"أِ": 50467,
|
| 46 |
+
"أِّ": 50475,
|
| 47 |
+
"أّ": 50469,
|
| 48 |
+
"أْ": 50470,
|
| 49 |
+
"أّْ": 50477,
|
| 50 |
+
"ؤً": 50505,
|
| 51 |
+
"ؤًا": 50513,
|
| 52 |
+
"ؤًّ": 50510,
|
| 53 |
+
"ؤٌ": 50504,
|
| 54 |
+
"ؤٌّ": 50512,
|
| 55 |
+
"ؤٍ": 50503,
|
| 56 |
+
"ؤٍّ": 50511,
|
| 57 |
+
"ؤَ": 50498,
|
| 58 |
+
"ؤَّ": 50506,
|
| 59 |
+
"ؤُ": 50500,
|
| 60 |
+
"ؤُّ": 50508,
|
| 61 |
+
"ؤِ": 50499,
|
| 62 |
+
"ؤِّ": 50507,
|
| 63 |
+
"ؤّ": 50501,
|
| 64 |
+
"ؤْ": 50502,
|
| 65 |
+
"ؤّْ": 50509,
|
| 66 |
+
"إً": 50489,
|
| 67 |
+
"إًا": 50497,
|
| 68 |
+
"إًّ": 50494,
|
| 69 |
+
"إٌ": 50488,
|
| 70 |
+
"إٌّ": 50496,
|
| 71 |
+
"إٍ": 50487,
|
| 72 |
+
"إٍّ": 50495,
|
| 73 |
+
"إَ": 50482,
|
| 74 |
+
"إَّ": 50490,
|
| 75 |
+
"إُ": 50484,
|
| 76 |
+
"إُّ": 50492,
|
| 77 |
+
"إِ": 50483,
|
| 78 |
+
"إِّ": 50491,
|
| 79 |
+
"إّ": 50485,
|
| 80 |
+
"إْ": 50486,
|
| 81 |
+
"إّْ": 50493,
|
| 82 |
+
"ئً": 50521,
|
| 83 |
+
"ئًا": 50529,
|
| 84 |
+
"ئًّ": 50526,
|
| 85 |
+
"ئٌ": 50520,
|
| 86 |
+
"ئٌّ": 50528,
|
| 87 |
+
"ئٍ": 50519,
|
| 88 |
+
"ئٍّ": 50527,
|
| 89 |
+
"ئَ": 50514,
|
| 90 |
+
"ئَّ": 50522,
|
| 91 |
+
"ئُ": 50516,
|
| 92 |
+
"ئُّ": 50524,
|
| 93 |
+
"ئِ": 50515,
|
| 94 |
+
"ئِّ": 50523,
|
| 95 |
+
"ئّ": 50517,
|
| 96 |
+
"ئْ": 50518,
|
| 97 |
+
"ئّْ": 50525,
|
| 98 |
+
"اً": 50441,
|
| 99 |
+
"اًا": 50449,
|
| 100 |
+
"اًّ": 50446,
|
| 101 |
+
"اٌ": 50440,
|
| 102 |
+
"اٌّ": 50448,
|
| 103 |
+
"اٍ": 50439,
|
| 104 |
+
"اٍّ": 50447,
|
| 105 |
+
"اَ": 50434,
|
| 106 |
+
"اَّ": 50442,
|
| 107 |
+
"اُ": 50436,
|
| 108 |
+
"اُّ": 50444,
|
| 109 |
+
"اِ": 50435,
|
| 110 |
+
"اِّ": 50443,
|
| 111 |
+
"اّ": 50437,
|
| 112 |
+
"اْ": 50438,
|
| 113 |
+
"اّْ": 50445,
|
| 114 |
+
"بً": 50009,
|
| 115 |
+
"بًا": 50017,
|
| 116 |
+
"بًّ": 50014,
|
| 117 |
+
"بٌ": 50008,
|
| 118 |
+
"بٌّ": 50016,
|
| 119 |
+
"بٍ": 50007,
|
| 120 |
+
"بٍّ": 50015,
|
| 121 |
+
"بَ": 50002,
|
| 122 |
+
"بَّ": 50010,
|
| 123 |
+
"بُ": 50004,
|
| 124 |
+
"بُّ": 50012,
|
| 125 |
+
"بِ": 50003,
|
| 126 |
+
"بِّ": 50011,
|
| 127 |
+
"بّ": 50005,
|
| 128 |
+
"بْ": 50006,
|
| 129 |
+
"بّْ": 50013,
|
| 130 |
+
"ةً": 50537,
|
| 131 |
+
"ةًا": 50545,
|
| 132 |
+
"ةًّ": 50542,
|
| 133 |
+
"ةٌ": 50536,
|
| 134 |
+
"ةٌّ": 50544,
|
| 135 |
+
"ةٍ": 50535,
|
| 136 |
+
"ةٍّ": 50543,
|
| 137 |
+
"ةَ": 50530,
|
| 138 |
+
"ةَّ": 50538,
|
| 139 |
+
"ةُ": 50532,
|
| 140 |
+
"ةُّ": 50540,
|
| 141 |
+
"ةِ": 50531,
|
| 142 |
+
"ةِّ": 50539,
|
| 143 |
+
"ةّ": 50533,
|
| 144 |
+
"ةْ": 50534,
|
| 145 |
+
"ةّْ": 50541,
|
| 146 |
+
"تً": 50025,
|
| 147 |
+
"تًا": 50033,
|
| 148 |
+
"تًّ": 50030,
|
| 149 |
+
"تٌ": 50024,
|
| 150 |
+
"تٌّ": 50032,
|
| 151 |
+
"تٍ": 50023,
|
| 152 |
+
"تٍّ": 50031,
|
| 153 |
+
"تَ": 50018,
|
| 154 |
+
"تَّ": 50026,
|
| 155 |
+
"تُ": 50020,
|
| 156 |
+
"تُّ": 50028,
|
| 157 |
+
"تِ": 50019,
|
| 158 |
+
"تِّ": 50027,
|
| 159 |
+
"تّ": 50021,
|
| 160 |
+
"تْ": 50022,
|
| 161 |
+
"تّْ": 50029,
|
| 162 |
+
"ثً": 50041,
|
| 163 |
+
"ثًا": 50049,
|
| 164 |
+
"ثًّ": 50046,
|
| 165 |
+
"ثٌ": 50040,
|
| 166 |
+
"ثٌّ": 50048,
|
| 167 |
+
"ثٍ": 50039,
|
| 168 |
+
"ثٍّ": 50047,
|
| 169 |
+
"ثَ": 50034,
|
| 170 |
+
"ثَّ": 50042,
|
| 171 |
+
"ثُ": 50036,
|
| 172 |
+
"ثُّ": 50044,
|
| 173 |
+
"ثِ": 50035,
|
| 174 |
+
"ثِّ": 50043,
|
| 175 |
+
"ثّ": 50037,
|
| 176 |
+
"ثْ": 50038,
|
| 177 |
+
"ثّْ": 50045,
|
| 178 |
+
"جً": 50057,
|
| 179 |
+
"جًا": 50065,
|
| 180 |
+
"جًّ": 50062,
|
| 181 |
+
"جٌ": 50056,
|
| 182 |
+
"جٌّ": 50064,
|
| 183 |
+
"جٍ": 50055,
|
| 184 |
+
"جٍّ": 50063,
|
| 185 |
+
"جَ": 50050,
|
| 186 |
+
"جَّ": 50058,
|
| 187 |
+
"جُ": 50052,
|
| 188 |
+
"جُّ": 50060,
|
| 189 |
+
"جِ": 50051,
|
| 190 |
+
"جِّ": 50059,
|
| 191 |
+
"جّ": 50053,
|
| 192 |
+
"جْ": 50054,
|
| 193 |
+
"جّْ": 50061,
|
| 194 |
+
"حً": 50073,
|
| 195 |
+
"حًا": 50081,
|
| 196 |
+
"حًّ": 50078,
|
| 197 |
+
"حٌ": 50072,
|
| 198 |
+
"حٌّ": 50080,
|
| 199 |
+
"حٍ": 50071,
|
| 200 |
+
"حٍّ": 50079,
|
| 201 |
+
"حَ": 50066,
|
| 202 |
+
"حَّ": 50074,
|
| 203 |
+
"حُ": 50068,
|
| 204 |
+
"حُّ": 50076,
|
| 205 |
+
"حِ": 50067,
|
| 206 |
+
"حِّ": 50075,
|
| 207 |
+
"حّ": 50069,
|
| 208 |
+
"حْ": 50070,
|
| 209 |
+
"حّْ": 50077,
|
| 210 |
+
"خً": 50089,
|
| 211 |
+
"خًا": 50097,
|
| 212 |
+
"خًّ": 50094,
|
| 213 |
+
"خٌ": 50088,
|
| 214 |
+
"خٌّ": 50096,
|
| 215 |
+
"خٍ": 50087,
|
| 216 |
+
"خٍّ": 50095,
|
| 217 |
+
"خَ": 50082,
|
| 218 |
+
"خَّ": 50090,
|
| 219 |
+
"خُ": 50084,
|
| 220 |
+
"خُّ": 50092,
|
| 221 |
+
"خِ": 50083,
|
| 222 |
+
"خِّ": 50091,
|
| 223 |
+
"خّ": 50085,
|
| 224 |
+
"خْ": 50086,
|
| 225 |
+
"خّْ": 50093,
|
| 226 |
+
"دً": 50105,
|
| 227 |
+
"دًا": 50113,
|
| 228 |
+
"دًّ": 50110,
|
| 229 |
+
"دٌ": 50104,
|
| 230 |
+
"دٌّ": 50112,
|
| 231 |
+
"دٍ": 50103,
|
| 232 |
+
"دٍّ": 50111,
|
| 233 |
+
"دَ": 50098,
|
| 234 |
+
"دَّ": 50106,
|
| 235 |
+
"دُ": 50100,
|
| 236 |
+
"دُّ": 50108,
|
| 237 |
+
"دِ": 50099,
|
| 238 |
+
"دِّ": 50107,
|
| 239 |
+
"دّ": 50101,
|
| 240 |
+
"دْ": 50102,
|
| 241 |
+
"دّْ": 50109,
|
| 242 |
+
"ذً": 50121,
|
| 243 |
+
"ذًا": 50129,
|
| 244 |
+
"ذًّ": 50126,
|
| 245 |
+
"ذٌ": 50120,
|
| 246 |
+
"ذٌّ": 50128,
|
| 247 |
+
"ذٍ": 50119,
|
| 248 |
+
"ذٍّ": 50127,
|
| 249 |
+
"ذَ": 50114,
|
| 250 |
+
"ذَّ": 50122,
|
| 251 |
+
"ذُ": 50116,
|
| 252 |
+
"ذُّ": 50124,
|
| 253 |
+
"ذِ": 50115,
|
| 254 |
+
"ذِّ": 50123,
|
| 255 |
+
"ذّ": 50117,
|
| 256 |
+
"ذْ": 50118,
|
| 257 |
+
"ذّْ": 50125,
|
| 258 |
+
"رً": 50137,
|
| 259 |
+
"رًا": 50145,
|
| 260 |
+
"رًّ": 50142,
|
| 261 |
+
"رٌ": 50136,
|
| 262 |
+
"رٌّ": 50144,
|
| 263 |
+
"رٍ": 50135,
|
| 264 |
+
"رٍّ": 50143,
|
| 265 |
+
"رَ": 50130,
|
| 266 |
+
"رَّ": 50138,
|
| 267 |
+
"رُ": 50132,
|
| 268 |
+
"رُّ": 50140,
|
| 269 |
+
"رِ": 50131,
|
| 270 |
+
"ر��ّ": 50139,
|
| 271 |
+
"رّ": 50133,
|
| 272 |
+
"رْ": 50134,
|
| 273 |
+
"رّْ": 50141,
|
| 274 |
+
"زً": 50153,
|
| 275 |
+
"زًا": 50161,
|
| 276 |
+
"زًّ": 50158,
|
| 277 |
+
"زٌ": 50152,
|
| 278 |
+
"زٌّ": 50160,
|
| 279 |
+
"زٍ": 50151,
|
| 280 |
+
"زٍّ": 50159,
|
| 281 |
+
"زَ": 50146,
|
| 282 |
+
"زَّ": 50154,
|
| 283 |
+
"زُ": 50148,
|
| 284 |
+
"زُّ": 50156,
|
| 285 |
+
"زِ": 50147,
|
| 286 |
+
"زِّ": 50155,
|
| 287 |
+
"زّ": 50149,
|
| 288 |
+
"زْ": 50150,
|
| 289 |
+
"زّْ": 50157,
|
| 290 |
+
"سً": 50169,
|
| 291 |
+
"سًا": 50177,
|
| 292 |
+
"سًّ": 50174,
|
| 293 |
+
"سٌ": 50168,
|
| 294 |
+
"سٌّ": 50176,
|
| 295 |
+
"سٍ": 50167,
|
| 296 |
+
"سٍّ": 50175,
|
| 297 |
+
"سَ": 50162,
|
| 298 |
+
"سَّ": 50170,
|
| 299 |
+
"سُ": 50164,
|
| 300 |
+
"سُّ": 50172,
|
| 301 |
+
"سِ": 50163,
|
| 302 |
+
"سِّ": 50171,
|
| 303 |
+
"سّ": 50165,
|
| 304 |
+
"سْ": 50166,
|
| 305 |
+
"سّْ": 50173,
|
| 306 |
+
"شً": 50185,
|
| 307 |
+
"شًا": 50193,
|
| 308 |
+
"شًّ": 50190,
|
| 309 |
+
"شٌ": 50184,
|
| 310 |
+
"شٌّ": 50192,
|
| 311 |
+
"شٍ": 50183,
|
| 312 |
+
"شٍّ": 50191,
|
| 313 |
+
"شَ": 50178,
|
| 314 |
+
"شَّ": 50186,
|
| 315 |
+
"شُ": 50180,
|
| 316 |
+
"شُّ": 50188,
|
| 317 |
+
"شِ": 50179,
|
| 318 |
+
"شِّ": 50187,
|
| 319 |
+
"شّ": 50181,
|
| 320 |
+
"شْ": 50182,
|
| 321 |
+
"شّْ": 50189,
|
| 322 |
+
"صً": 50201,
|
| 323 |
+
"صًا": 50209,
|
| 324 |
+
"صًّ": 50206,
|
| 325 |
+
"صٌ": 50200,
|
| 326 |
+
"صٌّ": 50208,
|
| 327 |
+
"صٍ": 50199,
|
| 328 |
+
"صٍّ": 50207,
|
| 329 |
+
"صَ": 50194,
|
| 330 |
+
"صَّ": 50202,
|
| 331 |
+
"صُ": 50196,
|
| 332 |
+
"صُّ": 50204,
|
| 333 |
+
"صِ": 50195,
|
| 334 |
+
"صِّ": 50203,
|
| 335 |
+
"صّ": 50197,
|
| 336 |
+
"صْ": 50198,
|
| 337 |
+
"صّْ": 50205,
|
| 338 |
+
"ضً": 50217,
|
| 339 |
+
"ضًا": 50225,
|
| 340 |
+
"ضًّ": 50222,
|
| 341 |
+
"ضٌ": 50216,
|
| 342 |
+
"ضٌّ": 50224,
|
| 343 |
+
"ضٍ": 50215,
|
| 344 |
+
"ضٍّ": 50223,
|
| 345 |
+
"ضَ": 50210,
|
| 346 |
+
"ضَّ": 50218,
|
| 347 |
+
"ضُ": 50212,
|
| 348 |
+
"ضُّ": 50220,
|
| 349 |
+
"ضِ": 50211,
|
| 350 |
+
"ضِّ": 50219,
|
| 351 |
+
"ضّ": 50213,
|
| 352 |
+
"ضْ": 50214,
|
| 353 |
+
"ضّْ": 50221,
|
| 354 |
+
"طً": 50233,
|
| 355 |
+
"طًا": 50241,
|
| 356 |
+
"طًّ": 50238,
|
| 357 |
+
"طٌ": 50232,
|
| 358 |
+
"طٌّ": 50240,
|
| 359 |
+
"طٍ": 50231,
|
| 360 |
+
"طٍّ": 50239,
|
| 361 |
+
"طَ": 50226,
|
| 362 |
+
"طَّ": 50234,
|
| 363 |
+
"طُ": 50228,
|
| 364 |
+
"طُّ": 50236,
|
| 365 |
+
"طِ": 50227,
|
| 366 |
+
"طِّ": 50235,
|
| 367 |
+
"طّ": 50229,
|
| 368 |
+
"طْ": 50230,
|
| 369 |
+
"طّْ": 50237,
|
| 370 |
+
"ظً": 50249,
|
| 371 |
+
"ظًا": 50257,
|
| 372 |
+
"ظًّ": 50254,
|
| 373 |
+
"ظٌ": 50248,
|
| 374 |
+
"ظٌّ": 50256,
|
| 375 |
+
"ظٍ": 50247,
|
| 376 |
+
"ظٍّ": 50255,
|
| 377 |
+
"ظَ": 50242,
|
| 378 |
+
"ظَّ": 50250,
|
| 379 |
+
"ظُ": 50244,
|
| 380 |
+
"ظُّ": 50252,
|
| 381 |
+
"ظِ": 50243,
|
| 382 |
+
"ظِّ": 50251,
|
| 383 |
+
"ظّ": 50245,
|
| 384 |
+
"ظْ": 50246,
|
| 385 |
+
"ظّْ": 50253,
|
| 386 |
+
"عً": 50265,
|
| 387 |
+
"عًا": 50273,
|
| 388 |
+
"عًّ": 50270,
|
| 389 |
+
"عٌ": 50264,
|
| 390 |
+
"عٌّ": 50272,
|
| 391 |
+
"عٍ": 50263,
|
| 392 |
+
"عٍّ": 50271,
|
| 393 |
+
"عَ": 50258,
|
| 394 |
+
"عَّ": 50266,
|
| 395 |
+
"عُ": 50260,
|
| 396 |
+
"عُّ": 50268,
|
| 397 |
+
"عِ": 50259,
|
| 398 |
+
"عِّ": 50267,
|
| 399 |
+
"عّ": 50261,
|
| 400 |
+
"عْ": 50262,
|
| 401 |
+
"عّْ": 50269,
|
| 402 |
+
"غً": 50281,
|
| 403 |
+
"غًا": 50289,
|
| 404 |
+
"غًّ": 50286,
|
| 405 |
+
"غٌ": 50280,
|
| 406 |
+
"غٌّ": 50288,
|
| 407 |
+
"غٍ": 50279,
|
| 408 |
+
"غٍّ": 50287,
|
| 409 |
+
"غَ": 50274,
|
| 410 |
+
"غَّ": 50282,
|
| 411 |
+
"غُ": 50276,
|
| 412 |
+
"غُّ": 50284,
|
| 413 |
+
"غِ": 50275,
|
| 414 |
+
"غِّ": 50283,
|
| 415 |
+
"غّ": 50277,
|
| 416 |
+
"غْ": 50278,
|
| 417 |
+
"غّْ": 50285,
|
| 418 |
+
"فً": 50297,
|
| 419 |
+
"فًا": 50305,
|
| 420 |
+
"فًّ": 50302,
|
| 421 |
+
"فٌ": 50296,
|
| 422 |
+
"فٌّ": 50304,
|
| 423 |
+
"فٍ": 50295,
|
| 424 |
+
"فٍّ": 50303,
|
| 425 |
+
"فَ": 50290,
|
| 426 |
+
"فَّ": 50298,
|
| 427 |
+
"فُ": 50292,
|
| 428 |
+
"فُّ": 50300,
|
| 429 |
+
"فِ": 50291,
|
| 430 |
+
"فِّ": 50299,
|
| 431 |
+
"فّ": 50293,
|
| 432 |
+
"فْ": 50294,
|
| 433 |
+
"فّْ": 50301,
|
| 434 |
+
"قً": 50313,
|
| 435 |
+
"قًا": 50321,
|
| 436 |
+
"قًّ": 50318,
|
| 437 |
+
"قٌ": 50312,
|
| 438 |
+
"قٌّ": 50320,
|
| 439 |
+
"قٍ": 50311,
|
| 440 |
+
"قٍّ": 50319,
|
| 441 |
+
"قَ": 50306,
|
| 442 |
+
"قَّ": 50314,
|
| 443 |
+
"قُ": 50308,
|
| 444 |
+
"قُّ": 50316,
|
| 445 |
+
"قِ": 50307,
|
| 446 |
+
"قِّ": 50315,
|
| 447 |
+
"قّ": 50309,
|
| 448 |
+
"قْ": 50310,
|
| 449 |
+
"قّْ": 50317,
|
| 450 |
+
"كً": 50329,
|
| 451 |
+
"كًا": 50337,
|
| 452 |
+
"كًّ": 50334,
|
| 453 |
+
"كٌ": 50328,
|
| 454 |
+
"كٌّ": 50336,
|
| 455 |
+
"كٍ": 50327,
|
| 456 |
+
"كٍّ": 50335,
|
| 457 |
+
"كَ": 50322,
|
| 458 |
+
"كَّ": 50330,
|
| 459 |
+
"كُ": 50324,
|
| 460 |
+
"كُّ": 50332,
|
| 461 |
+
"كِ": 50323,
|
| 462 |
+
"كِّ": 50331,
|
| 463 |
+
"كّ": 50325,
|
| 464 |
+
"كْ": 50326,
|
| 465 |
+
"كّْ": 50333,
|
| 466 |
+
"لً": 50345,
|
| 467 |
+
"لًا": 50353,
|
| 468 |
+
"لًّ": 50350,
|
| 469 |
+
"لٌ": 50344,
|
| 470 |
+
"لٌّ": 50352,
|
| 471 |
+
"لٍ": 50343,
|
| 472 |
+
"لٍّ": 50351,
|
| 473 |
+
"لَ": 50338,
|
| 474 |
+
"لَّ": 50346,
|
| 475 |
+
"لُ": 50340,
|
| 476 |
+
"لُّ": 50348,
|
| 477 |
+
"لِ": 50339,
|
| 478 |
+
"لِّ": 50347,
|
| 479 |
+
"لّ": 50341,
|
| 480 |
+
"لْ": 50342,
|
| 481 |
+
"لّْ": 50349,
|
| 482 |
+
"مً": 50361,
|
| 483 |
+
"مًا": 50369,
|
| 484 |
+
"مًّ": 50366,
|
| 485 |
+
"مٌ": 50360,
|
| 486 |
+
"مٌّ": 50368,
|
| 487 |
+
"مٍ": 50359,
|
| 488 |
+
"مٍّ": 50367,
|
| 489 |
+
"مَ": 50354,
|
| 490 |
+
"مَّ": 50362,
|
| 491 |
+
"مُ": 50356,
|
| 492 |
+
"مُّ": 50364,
|
| 493 |
+
"مِ": 50355,
|
| 494 |
+
"مِّ": 50363,
|
| 495 |
+
"مّ": 50357,
|
| 496 |
+
"مْ": 50358,
|
| 497 |
+
"مّْ": 50365,
|
| 498 |
+
"نً": 50377,
|
| 499 |
+
"نًا": 50385,
|
| 500 |
+
"نًّ": 50382,
|
| 501 |
+
"نٌ": 50376,
|
| 502 |
+
"نٌّ": 50384,
|
| 503 |
+
"نٍ": 50375,
|
| 504 |
+
"نٍّ": 50383,
|
| 505 |
+
"نَ": 50370,
|
| 506 |
+
"نَّ": 50378,
|
| 507 |
+
"نُ": 50372,
|
| 508 |
+
"نُّ": 50380,
|
| 509 |
+
"نِ": 50371,
|
| 510 |
+
"نِّ": 50379,
|
| 511 |
+
"نّ": 50373,
|
| 512 |
+
"نْ": 50374,
|
| 513 |
+
"نّْ": 50381,
|
| 514 |
+
"هً": 50393,
|
| 515 |
+
"هًا": 50401,
|
| 516 |
+
"هًّ": 50398,
|
| 517 |
+
"هٌ": 50392,
|
| 518 |
+
"هٌّ": 50400,
|
| 519 |
+
"هٍ": 50391,
|
| 520 |
+
"هٍّ": 50399,
|
| 521 |
+
"هَ": 50386,
|
| 522 |
+
"هَّ": 50394,
|
| 523 |
+
"هُ": 50388,
|
| 524 |
+
"هُّ": 50396,
|
| 525 |
+
"هِ": 50387,
|
| 526 |
+
"هِّ": 50395,
|
| 527 |
+
"هّ": 50389,
|
| 528 |
+
"هْ": 50390,
|
| 529 |
+
"هّْ": 50397,
|
| 530 |
+
"وً": 50409,
|
| 531 |
+
"وًا": 50417,
|
| 532 |
+
"وًّ": 50414,
|
| 533 |
+
"وٌ": 50408,
|
| 534 |
+
"وٌّ": 50416,
|
| 535 |
+
"وٍ": 50407,
|
| 536 |
+
"وٍّ": 50415,
|
| 537 |
+
"وَ": 50402,
|
| 538 |
+
"وَّ": 50410,
|
| 539 |
+
"وُ": 50404,
|
| 540 |
+
"وُّ": 50412,
|
| 541 |
+
"وِ": 50403,
|
| 542 |
+
"وِّ": 50411,
|
| 543 |
+
"وّ": 50405,
|
| 544 |
+
"وْ": 50406,
|
| 545 |
+
"وّْ": 50413,
|
| 546 |
+
"ىً": 50457,
|
| 547 |
+
"ىًا": 50465,
|
| 548 |
+
"ىًّ": 50462,
|
| 549 |
+
"ىٌ": 50456,
|
| 550 |
+
"ىٌّ": 50464,
|
| 551 |
+
"ىٍ": 50455,
|
| 552 |
+
"ىٍّ": 50463,
|
| 553 |
+
"ىَ": 50450,
|
| 554 |
+
"ىَّ": 50458,
|
| 555 |
+
"ىُ": 50452,
|
| 556 |
+
"ىُّ": 50460,
|
| 557 |
+
"ىِ": 50451,
|
| 558 |
+
"ىِّ": 50459,
|
| 559 |
+
"ىّ": 50453,
|
| 560 |
+
"ىْ": 50454,
|
| 561 |
+
"ىّْ": 50461,
|
| 562 |
+
"يً": 50425,
|
| 563 |
+
"يًا": 50433,
|
| 564 |
+
"يًّ": 50430,
|
| 565 |
+
"يٌ": 50424,
|
| 566 |
+
"يٌّ": 50432,
|
| 567 |
+
"يٍ": 50423,
|
| 568 |
+
"يٍّ": 50431,
|
| 569 |
+
"يَ": 50418,
|
| 570 |
+
"يَّ": 50426,
|
| 571 |
+
"يُ": 50420,
|
| 572 |
+
"يُّ": 50428,
|
| 573 |
+
"يِ": 50419,
|
| 574 |
+
"يِّ": 50427,
|
| 575 |
+
"يّ": 50421,
|
| 576 |
+
"يْ": 50422,
|
| 577 |
+
"يّْ": 50429,
|
| 578 |
+
"ً": 50585,
|
| 579 |
+
"ًا": 50593,
|
| 580 |
+
"ًّ": 50590,
|
| 581 |
+
"ٌ": 50584,
|
| 582 |
+
"ٌّ": 50592,
|
| 583 |
+
"ٍ": 50583,
|
| 584 |
+
"ٍّ": 50591,
|
| 585 |
+
"َ": 50578,
|
| 586 |
+
"َّ": 50586,
|
| 587 |
+
"ُ": 50580,
|
| 588 |
+
"ُّ": 50588,
|
| 589 |
+
"ِ": 50579,
|
| 590 |
+
"ِّ": 50587,
|
| 591 |
+
"ّ": 50581,
|
| 592 |
+
"ْ": 50582,
|
| 593 |
+
"ّْ": 50589
|
| 594 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_bias_logits": false,
|
| 5 |
+
"add_final_layer_norm": true,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MBartForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"classif_dropout": 0.1,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 768,
|
| 14 |
+
"decoder_attention_heads": 12,
|
| 15 |
+
"decoder_ffn_dim": 3072,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 6,
|
| 18 |
+
"decoder_start_token_id": 2,
|
| 19 |
+
"do_blenderbot_90_layernorm": false,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"extra_pos_embeddings": 2,
|
| 28 |
+
"force_bos_token_to_be_generated": false,
|
| 29 |
+
"forced_eos_token_id": 2,
|
| 30 |
+
"gradient_checkpointing": false,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"max_position_embeddings": 1024,
|
| 44 |
+
"model_type": "mbart",
|
| 45 |
+
"no_repeat_ngram_size": null,
|
| 46 |
+
"normalize_before": true,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": null,
|
| 49 |
+
"num_hidden_layers": 6,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"scale_embedding": false,
|
| 52 |
+
"static_position_embeddings": false,
|
| 53 |
+
"tokenizer_class": "BarthezTokenizer",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.51.3",
|
| 56 |
+
"use_cache": false,
|
| 57 |
+
"vocab_size": 50594
|
| 58 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f404e3f4f90eb1c1cde1e5523689e69cf78cb4c229aa7e98046e7fe7b32126b2
|
| 3 |
+
size 558937304
|
runs/Apr27_00-02-14_ip-10-192-12-77/events.out.tfevents.1745712146.ip-10-192-12-77.2238.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8aaf646e32e5d97edf12aecfe225f14a9f3b53a7c8a5558676116e68ec343ec
|
| 3 |
+
size 6654
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
|
| 3 |
+
size 1315170
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d90aa71a71a1d76f2ed06c895dd497816eb3dae89167b7fee36b6c5811b95be2
|
| 3 |
+
size 5841
|