Training in progress, step 150
Browse files- config.json +306 -306
- model.safetensors +1 -1
- runs/Sep27_14-16-48_d22a93eda77c/events.out.tfevents.1758982611.d22a93eda77c.63.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
"classifier_activation": "gelu",
|
| 9 |
"classifier_bias": false,
|
| 10 |
"classifier_dropout": 0.0,
|
|
@@ -12,322 +12,321 @@
|
|
| 12 |
"cls_token_id": 50281,
|
| 13 |
"decoder_bias": true,
|
| 14 |
"deterministic_flash_attn": false,
|
| 15 |
-
"dtype": "float32",
|
| 16 |
"embedding_dropout": 0.0,
|
| 17 |
-
"eos_token_id":
|
| 18 |
"global_attn_every_n_layers": 3,
|
| 19 |
"global_rope_theta": 160000.0,
|
| 20 |
"gradient_checkpointing": false,
|
| 21 |
"hidden_activation": "gelu",
|
| 22 |
"hidden_size": 1024,
|
| 23 |
"id2label": {
|
| 24 |
-
"0": "
|
| 25 |
-
"1": "
|
| 26 |
-
"2": "
|
| 27 |
-
"3": "
|
| 28 |
-
"4": "
|
| 29 |
-
"5": "
|
| 30 |
-
"6": "
|
| 31 |
-
"7": "
|
| 32 |
-
"8": "
|
| 33 |
-
"9": "
|
| 34 |
-
"10": "
|
| 35 |
-
"11": "
|
| 36 |
-
"12": "
|
| 37 |
-
"13": "
|
| 38 |
-
"14": "
|
| 39 |
-
"15": "
|
| 40 |
-
"16": "
|
| 41 |
-
"17": "
|
| 42 |
-
"18": "
|
| 43 |
-
"19": "
|
| 44 |
-
"20": "
|
| 45 |
-
"21": "
|
| 46 |
-
"22": "
|
| 47 |
-
"23": "
|
| 48 |
-
"24": "
|
| 49 |
-
"25": "
|
| 50 |
-
"26": "
|
| 51 |
-
"27": "
|
| 52 |
-
"28": "
|
| 53 |
-
"29": "
|
| 54 |
-
"30": "
|
| 55 |
-
"31": "
|
| 56 |
-
"32": "
|
| 57 |
-
"33": "
|
| 58 |
-
"34": "
|
| 59 |
-
"35": "
|
| 60 |
-
"36": "
|
| 61 |
-
"37": "
|
| 62 |
-
"38": "
|
| 63 |
-
"39": "
|
| 64 |
-
"40": "
|
| 65 |
-
"41": "
|
| 66 |
-
"42": "
|
| 67 |
-
"43": "
|
| 68 |
-
"44": "
|
| 69 |
-
"45": "
|
| 70 |
-
"46": "
|
| 71 |
-
"47": "
|
| 72 |
-
"48": "
|
| 73 |
-
"49": "
|
| 74 |
-
"50": "
|
| 75 |
-
"51": "
|
| 76 |
-
"52": "
|
| 77 |
-
"53": "
|
| 78 |
-
"54": "
|
| 79 |
-
"55": "
|
| 80 |
-
"56": "
|
| 81 |
-
"57": "
|
| 82 |
-
"58": "
|
| 83 |
-
"59": "
|
| 84 |
-
"60": "
|
| 85 |
-
"61": "
|
| 86 |
-
"62": "
|
| 87 |
-
"63": "
|
| 88 |
-
"64": "
|
| 89 |
-
"65": "
|
| 90 |
-
"66": "
|
| 91 |
-
"67": "
|
| 92 |
-
"68": "
|
| 93 |
-
"69": "
|
| 94 |
-
"70": "
|
| 95 |
-
"71": "
|
| 96 |
-
"72": "
|
| 97 |
-
"73": "
|
| 98 |
-
"74": "
|
| 99 |
-
"75": "
|
| 100 |
-
"76": "
|
| 101 |
-
"77": "
|
| 102 |
-
"78": "
|
| 103 |
-
"79": "
|
| 104 |
-
"80": "
|
| 105 |
-
"81": "
|
| 106 |
-
"82": "
|
| 107 |
-
"83": "
|
| 108 |
-
"84": "
|
| 109 |
-
"85": "
|
| 110 |
-
"86": "
|
| 111 |
-
"87": "
|
| 112 |
-
"88": "
|
| 113 |
-
"89": "
|
| 114 |
-
"90": "
|
| 115 |
-
"91": "
|
| 116 |
-
"92": "
|
| 117 |
-
"93": "
|
| 118 |
-
"94": "
|
| 119 |
-
"95": "
|
| 120 |
-
"96": "
|
| 121 |
-
"97": "
|
| 122 |
-
"98": "
|
| 123 |
-
"99": "
|
| 124 |
-
"100": "
|
| 125 |
-
"101": "
|
| 126 |
-
"102": "
|
| 127 |
-
"103": "
|
| 128 |
-
"104": "
|
| 129 |
-
"105": "
|
| 130 |
-
"106": "
|
| 131 |
-
"107": "
|
| 132 |
-
"108": "
|
| 133 |
-
"109": "
|
| 134 |
-
"110": "
|
| 135 |
-
"111": "
|
| 136 |
-
"112": "
|
| 137 |
-
"113": "
|
| 138 |
-
"114": "
|
| 139 |
-
"115": "
|
| 140 |
-
"116": "
|
| 141 |
-
"117": "
|
| 142 |
-
"118": "
|
| 143 |
-
"119": "
|
| 144 |
-
"120": "
|
| 145 |
-
"121": "
|
| 146 |
-
"122": "
|
| 147 |
-
"123": "
|
| 148 |
-
"124": "
|
| 149 |
-
"125": "
|
| 150 |
-
"126": "
|
| 151 |
-
"127": "
|
| 152 |
-
"128": "
|
| 153 |
-
"129": "
|
| 154 |
-
"130": "
|
| 155 |
-
"131": "
|
| 156 |
-
"132": "
|
| 157 |
-
"133": "
|
| 158 |
-
"134": "
|
| 159 |
-
"135": "
|
| 160 |
-
"136": "
|
| 161 |
-
"137": "
|
| 162 |
-
"138": "
|
| 163 |
-
"139": "
|
| 164 |
-
"140": "
|
| 165 |
-
"141": "
|
| 166 |
-
"142": "
|
| 167 |
-
"143": "
|
| 168 |
-
"144": "
|
| 169 |
-
"145": "
|
| 170 |
-
"146": "
|
| 171 |
-
"147": "
|
| 172 |
-
"148": "
|
| 173 |
-
"149": "
|
| 174 |
-
"150": "
|
| 175 |
},
|
| 176 |
"initializer_cutoff_factor": 2.0,
|
| 177 |
"initializer_range": 0.02,
|
| 178 |
"intermediate_size": 2624,
|
| 179 |
"label2id": {
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"
|
| 203 |
-
"
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
| 220 |
-
"
|
| 221 |
-
"
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"
|
| 226 |
-
"
|
| 227 |
-
"
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"
|
| 232 |
-
"
|
| 233 |
-
"
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"
|
| 251 |
-
"
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
| 258 |
-
"
|
| 259 |
-
"
|
| 260 |
-
"
|
| 261 |
-
"
|
| 262 |
-
"
|
| 263 |
-
"
|
| 264 |
-
"
|
| 265 |
-
"
|
| 266 |
-
"
|
| 267 |
-
"
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"
|
| 275 |
-
"
|
| 276 |
-
"
|
| 277 |
-
"
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
| 281 |
-
"
|
| 282 |
-
"
|
| 283 |
-
"
|
| 284 |
-
"
|
| 285 |
-
"
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
| 290 |
-
"
|
| 291 |
-
"
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
| 295 |
-
"
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
"
|
| 303 |
-
"
|
| 304 |
-
"
|
| 305 |
-
"
|
| 306 |
-
"
|
| 307 |
-
"
|
| 308 |
-
"
|
| 309 |
-
"
|
| 310 |
-
"
|
| 311 |
-
"
|
| 312 |
-
"
|
| 313 |
-
"
|
| 314 |
-
"
|
| 315 |
-
"
|
| 316 |
-
"
|
| 317 |
-
"
|
| 318 |
-
"
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
"
|
| 323 |
-
"
|
| 324 |
-
"
|
| 325 |
-
"
|
| 326 |
-
"
|
| 327 |
-
"
|
| 328 |
-
"
|
| 329 |
-
"
|
| 330 |
-
"
|
| 331 |
},
|
| 332 |
"layer_norm_eps": 1e-05,
|
| 333 |
"local_attention": 128,
|
|
@@ -347,6 +346,7 @@
|
|
| 347 |
"sep_token_id": 50282,
|
| 348 |
"sparse_pred_ignore_index": -100,
|
| 349 |
"sparse_prediction": false,
|
| 350 |
-
"
|
|
|
|
| 351 |
"vocab_size": 50368
|
| 352 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
"classifier_activation": "gelu",
|
| 9 |
"classifier_bias": false,
|
| 10 |
"classifier_dropout": 0.0,
|
|
|
|
| 12 |
"cls_token_id": 50281,
|
| 13 |
"decoder_bias": true,
|
| 14 |
"deterministic_flash_attn": false,
|
|
|
|
| 15 |
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
"global_attn_every_n_layers": 3,
|
| 18 |
"global_rope_theta": 160000.0,
|
| 19 |
"gradient_checkpointing": false,
|
| 20 |
"hidden_activation": "gelu",
|
| 21 |
"hidden_size": 1024,
|
| 22 |
"id2label": {
|
| 23 |
+
"0": "LABEL_0",
|
| 24 |
+
"1": "LABEL_1",
|
| 25 |
+
"2": "LABEL_2",
|
| 26 |
+
"3": "LABEL_3",
|
| 27 |
+
"4": "LABEL_4",
|
| 28 |
+
"5": "LABEL_5",
|
| 29 |
+
"6": "LABEL_6",
|
| 30 |
+
"7": "LABEL_7",
|
| 31 |
+
"8": "LABEL_8",
|
| 32 |
+
"9": "LABEL_9",
|
| 33 |
+
"10": "LABEL_10",
|
| 34 |
+
"11": "LABEL_11",
|
| 35 |
+
"12": "LABEL_12",
|
| 36 |
+
"13": "LABEL_13",
|
| 37 |
+
"14": "LABEL_14",
|
| 38 |
+
"15": "LABEL_15",
|
| 39 |
+
"16": "LABEL_16",
|
| 40 |
+
"17": "LABEL_17",
|
| 41 |
+
"18": "LABEL_18",
|
| 42 |
+
"19": "LABEL_19",
|
| 43 |
+
"20": "LABEL_20",
|
| 44 |
+
"21": "LABEL_21",
|
| 45 |
+
"22": "LABEL_22",
|
| 46 |
+
"23": "LABEL_23",
|
| 47 |
+
"24": "LABEL_24",
|
| 48 |
+
"25": "LABEL_25",
|
| 49 |
+
"26": "LABEL_26",
|
| 50 |
+
"27": "LABEL_27",
|
| 51 |
+
"28": "LABEL_28",
|
| 52 |
+
"29": "LABEL_29",
|
| 53 |
+
"30": "LABEL_30",
|
| 54 |
+
"31": "LABEL_31",
|
| 55 |
+
"32": "LABEL_32",
|
| 56 |
+
"33": "LABEL_33",
|
| 57 |
+
"34": "LABEL_34",
|
| 58 |
+
"35": "LABEL_35",
|
| 59 |
+
"36": "LABEL_36",
|
| 60 |
+
"37": "LABEL_37",
|
| 61 |
+
"38": "LABEL_38",
|
| 62 |
+
"39": "LABEL_39",
|
| 63 |
+
"40": "LABEL_40",
|
| 64 |
+
"41": "LABEL_41",
|
| 65 |
+
"42": "LABEL_42",
|
| 66 |
+
"43": "LABEL_43",
|
| 67 |
+
"44": "LABEL_44",
|
| 68 |
+
"45": "LABEL_45",
|
| 69 |
+
"46": "LABEL_46",
|
| 70 |
+
"47": "LABEL_47",
|
| 71 |
+
"48": "LABEL_48",
|
| 72 |
+
"49": "LABEL_49",
|
| 73 |
+
"50": "LABEL_50",
|
| 74 |
+
"51": "LABEL_51",
|
| 75 |
+
"52": "LABEL_52",
|
| 76 |
+
"53": "LABEL_53",
|
| 77 |
+
"54": "LABEL_54",
|
| 78 |
+
"55": "LABEL_55",
|
| 79 |
+
"56": "LABEL_56",
|
| 80 |
+
"57": "LABEL_57",
|
| 81 |
+
"58": "LABEL_58",
|
| 82 |
+
"59": "LABEL_59",
|
| 83 |
+
"60": "LABEL_60",
|
| 84 |
+
"61": "LABEL_61",
|
| 85 |
+
"62": "LABEL_62",
|
| 86 |
+
"63": "LABEL_63",
|
| 87 |
+
"64": "LABEL_64",
|
| 88 |
+
"65": "LABEL_65",
|
| 89 |
+
"66": "LABEL_66",
|
| 90 |
+
"67": "LABEL_67",
|
| 91 |
+
"68": "LABEL_68",
|
| 92 |
+
"69": "LABEL_69",
|
| 93 |
+
"70": "LABEL_70",
|
| 94 |
+
"71": "LABEL_71",
|
| 95 |
+
"72": "LABEL_72",
|
| 96 |
+
"73": "LABEL_73",
|
| 97 |
+
"74": "LABEL_74",
|
| 98 |
+
"75": "LABEL_75",
|
| 99 |
+
"76": "LABEL_76",
|
| 100 |
+
"77": "LABEL_77",
|
| 101 |
+
"78": "LABEL_78",
|
| 102 |
+
"79": "LABEL_79",
|
| 103 |
+
"80": "LABEL_80",
|
| 104 |
+
"81": "LABEL_81",
|
| 105 |
+
"82": "LABEL_82",
|
| 106 |
+
"83": "LABEL_83",
|
| 107 |
+
"84": "LABEL_84",
|
| 108 |
+
"85": "LABEL_85",
|
| 109 |
+
"86": "LABEL_86",
|
| 110 |
+
"87": "LABEL_87",
|
| 111 |
+
"88": "LABEL_88",
|
| 112 |
+
"89": "LABEL_89",
|
| 113 |
+
"90": "LABEL_90",
|
| 114 |
+
"91": "LABEL_91",
|
| 115 |
+
"92": "LABEL_92",
|
| 116 |
+
"93": "LABEL_93",
|
| 117 |
+
"94": "LABEL_94",
|
| 118 |
+
"95": "LABEL_95",
|
| 119 |
+
"96": "LABEL_96",
|
| 120 |
+
"97": "LABEL_97",
|
| 121 |
+
"98": "LABEL_98",
|
| 122 |
+
"99": "LABEL_99",
|
| 123 |
+
"100": "LABEL_100",
|
| 124 |
+
"101": "LABEL_101",
|
| 125 |
+
"102": "LABEL_102",
|
| 126 |
+
"103": "LABEL_103",
|
| 127 |
+
"104": "LABEL_104",
|
| 128 |
+
"105": "LABEL_105",
|
| 129 |
+
"106": "LABEL_106",
|
| 130 |
+
"107": "LABEL_107",
|
| 131 |
+
"108": "LABEL_108",
|
| 132 |
+
"109": "LABEL_109",
|
| 133 |
+
"110": "LABEL_110",
|
| 134 |
+
"111": "LABEL_111",
|
| 135 |
+
"112": "LABEL_112",
|
| 136 |
+
"113": "LABEL_113",
|
| 137 |
+
"114": "LABEL_114",
|
| 138 |
+
"115": "LABEL_115",
|
| 139 |
+
"116": "LABEL_116",
|
| 140 |
+
"117": "LABEL_117",
|
| 141 |
+
"118": "LABEL_118",
|
| 142 |
+
"119": "LABEL_119",
|
| 143 |
+
"120": "LABEL_120",
|
| 144 |
+
"121": "LABEL_121",
|
| 145 |
+
"122": "LABEL_122",
|
| 146 |
+
"123": "LABEL_123",
|
| 147 |
+
"124": "LABEL_124",
|
| 148 |
+
"125": "LABEL_125",
|
| 149 |
+
"126": "LABEL_126",
|
| 150 |
+
"127": "LABEL_127",
|
| 151 |
+
"128": "LABEL_128",
|
| 152 |
+
"129": "LABEL_129",
|
| 153 |
+
"130": "LABEL_130",
|
| 154 |
+
"131": "LABEL_131",
|
| 155 |
+
"132": "LABEL_132",
|
| 156 |
+
"133": "LABEL_133",
|
| 157 |
+
"134": "LABEL_134",
|
| 158 |
+
"135": "LABEL_135",
|
| 159 |
+
"136": "LABEL_136",
|
| 160 |
+
"137": "LABEL_137",
|
| 161 |
+
"138": "LABEL_138",
|
| 162 |
+
"139": "LABEL_139",
|
| 163 |
+
"140": "LABEL_140",
|
| 164 |
+
"141": "LABEL_141",
|
| 165 |
+
"142": "LABEL_142",
|
| 166 |
+
"143": "LABEL_143",
|
| 167 |
+
"144": "LABEL_144",
|
| 168 |
+
"145": "LABEL_145",
|
| 169 |
+
"146": "LABEL_146",
|
| 170 |
+
"147": "LABEL_147",
|
| 171 |
+
"148": "LABEL_148",
|
| 172 |
+
"149": "LABEL_149",
|
| 173 |
+
"150": "LABEL_150"
|
| 174 |
},
|
| 175 |
"initializer_cutoff_factor": 2.0,
|
| 176 |
"initializer_range": 0.02,
|
| 177 |
"intermediate_size": 2624,
|
| 178 |
"label2id": {
|
| 179 |
+
"LABEL_0": 0,
|
| 180 |
+
"LABEL_1": 1,
|
| 181 |
+
"LABEL_10": 10,
|
| 182 |
+
"LABEL_100": 100,
|
| 183 |
+
"LABEL_101": 101,
|
| 184 |
+
"LABEL_102": 102,
|
| 185 |
+
"LABEL_103": 103,
|
| 186 |
+
"LABEL_104": 104,
|
| 187 |
+
"LABEL_105": 105,
|
| 188 |
+
"LABEL_106": 106,
|
| 189 |
+
"LABEL_107": 107,
|
| 190 |
+
"LABEL_108": 108,
|
| 191 |
+
"LABEL_109": 109,
|
| 192 |
+
"LABEL_11": 11,
|
| 193 |
+
"LABEL_110": 110,
|
| 194 |
+
"LABEL_111": 111,
|
| 195 |
+
"LABEL_112": 112,
|
| 196 |
+
"LABEL_113": 113,
|
| 197 |
+
"LABEL_114": 114,
|
| 198 |
+
"LABEL_115": 115,
|
| 199 |
+
"LABEL_116": 116,
|
| 200 |
+
"LABEL_117": 117,
|
| 201 |
+
"LABEL_118": 118,
|
| 202 |
+
"LABEL_119": 119,
|
| 203 |
+
"LABEL_12": 12,
|
| 204 |
+
"LABEL_120": 120,
|
| 205 |
+
"LABEL_121": 121,
|
| 206 |
+
"LABEL_122": 122,
|
| 207 |
+
"LABEL_123": 123,
|
| 208 |
+
"LABEL_124": 124,
|
| 209 |
+
"LABEL_125": 125,
|
| 210 |
+
"LABEL_126": 126,
|
| 211 |
+
"LABEL_127": 127,
|
| 212 |
+
"LABEL_128": 128,
|
| 213 |
+
"LABEL_129": 129,
|
| 214 |
+
"LABEL_13": 13,
|
| 215 |
+
"LABEL_130": 130,
|
| 216 |
+
"LABEL_131": 131,
|
| 217 |
+
"LABEL_132": 132,
|
| 218 |
+
"LABEL_133": 133,
|
| 219 |
+
"LABEL_134": 134,
|
| 220 |
+
"LABEL_135": 135,
|
| 221 |
+
"LABEL_136": 136,
|
| 222 |
+
"LABEL_137": 137,
|
| 223 |
+
"LABEL_138": 138,
|
| 224 |
+
"LABEL_139": 139,
|
| 225 |
+
"LABEL_14": 14,
|
| 226 |
+
"LABEL_140": 140,
|
| 227 |
+
"LABEL_141": 141,
|
| 228 |
+
"LABEL_142": 142,
|
| 229 |
+
"LABEL_143": 143,
|
| 230 |
+
"LABEL_144": 144,
|
| 231 |
+
"LABEL_145": 145,
|
| 232 |
+
"LABEL_146": 146,
|
| 233 |
+
"LABEL_147": 147,
|
| 234 |
+
"LABEL_148": 148,
|
| 235 |
+
"LABEL_149": 149,
|
| 236 |
+
"LABEL_15": 15,
|
| 237 |
+
"LABEL_150": 150,
|
| 238 |
+
"LABEL_16": 16,
|
| 239 |
+
"LABEL_17": 17,
|
| 240 |
+
"LABEL_18": 18,
|
| 241 |
+
"LABEL_19": 19,
|
| 242 |
+
"LABEL_2": 2,
|
| 243 |
+
"LABEL_20": 20,
|
| 244 |
+
"LABEL_21": 21,
|
| 245 |
+
"LABEL_22": 22,
|
| 246 |
+
"LABEL_23": 23,
|
| 247 |
+
"LABEL_24": 24,
|
| 248 |
+
"LABEL_25": 25,
|
| 249 |
+
"LABEL_26": 26,
|
| 250 |
+
"LABEL_27": 27,
|
| 251 |
+
"LABEL_28": 28,
|
| 252 |
+
"LABEL_29": 29,
|
| 253 |
+
"LABEL_3": 3,
|
| 254 |
+
"LABEL_30": 30,
|
| 255 |
+
"LABEL_31": 31,
|
| 256 |
+
"LABEL_32": 32,
|
| 257 |
+
"LABEL_33": 33,
|
| 258 |
+
"LABEL_34": 34,
|
| 259 |
+
"LABEL_35": 35,
|
| 260 |
+
"LABEL_36": 36,
|
| 261 |
+
"LABEL_37": 37,
|
| 262 |
+
"LABEL_38": 38,
|
| 263 |
+
"LABEL_39": 39,
|
| 264 |
+
"LABEL_4": 4,
|
| 265 |
+
"LABEL_40": 40,
|
| 266 |
+
"LABEL_41": 41,
|
| 267 |
+
"LABEL_42": 42,
|
| 268 |
+
"LABEL_43": 43,
|
| 269 |
+
"LABEL_44": 44,
|
| 270 |
+
"LABEL_45": 45,
|
| 271 |
+
"LABEL_46": 46,
|
| 272 |
+
"LABEL_47": 47,
|
| 273 |
+
"LABEL_48": 48,
|
| 274 |
+
"LABEL_49": 49,
|
| 275 |
+
"LABEL_5": 5,
|
| 276 |
+
"LABEL_50": 50,
|
| 277 |
+
"LABEL_51": 51,
|
| 278 |
+
"LABEL_52": 52,
|
| 279 |
+
"LABEL_53": 53,
|
| 280 |
+
"LABEL_54": 54,
|
| 281 |
+
"LABEL_55": 55,
|
| 282 |
+
"LABEL_56": 56,
|
| 283 |
+
"LABEL_57": 57,
|
| 284 |
+
"LABEL_58": 58,
|
| 285 |
+
"LABEL_59": 59,
|
| 286 |
+
"LABEL_6": 6,
|
| 287 |
+
"LABEL_60": 60,
|
| 288 |
+
"LABEL_61": 61,
|
| 289 |
+
"LABEL_62": 62,
|
| 290 |
+
"LABEL_63": 63,
|
| 291 |
+
"LABEL_64": 64,
|
| 292 |
+
"LABEL_65": 65,
|
| 293 |
+
"LABEL_66": 66,
|
| 294 |
+
"LABEL_67": 67,
|
| 295 |
+
"LABEL_68": 68,
|
| 296 |
+
"LABEL_69": 69,
|
| 297 |
+
"LABEL_7": 7,
|
| 298 |
+
"LABEL_70": 70,
|
| 299 |
+
"LABEL_71": 71,
|
| 300 |
+
"LABEL_72": 72,
|
| 301 |
+
"LABEL_73": 73,
|
| 302 |
+
"LABEL_74": 74,
|
| 303 |
+
"LABEL_75": 75,
|
| 304 |
+
"LABEL_76": 76,
|
| 305 |
+
"LABEL_77": 77,
|
| 306 |
+
"LABEL_78": 78,
|
| 307 |
+
"LABEL_79": 79,
|
| 308 |
+
"LABEL_8": 8,
|
| 309 |
+
"LABEL_80": 80,
|
| 310 |
+
"LABEL_81": 81,
|
| 311 |
+
"LABEL_82": 82,
|
| 312 |
+
"LABEL_83": 83,
|
| 313 |
+
"LABEL_84": 84,
|
| 314 |
+
"LABEL_85": 85,
|
| 315 |
+
"LABEL_86": 86,
|
| 316 |
+
"LABEL_87": 87,
|
| 317 |
+
"LABEL_88": 88,
|
| 318 |
+
"LABEL_89": 89,
|
| 319 |
+
"LABEL_9": 9,
|
| 320 |
+
"LABEL_90": 90,
|
| 321 |
+
"LABEL_91": 91,
|
| 322 |
+
"LABEL_92": 92,
|
| 323 |
+
"LABEL_93": 93,
|
| 324 |
+
"LABEL_94": 94,
|
| 325 |
+
"LABEL_95": 95,
|
| 326 |
+
"LABEL_96": 96,
|
| 327 |
+
"LABEL_97": 97,
|
| 328 |
+
"LABEL_98": 98,
|
| 329 |
+
"LABEL_99": 99
|
| 330 |
},
|
| 331 |
"layer_norm_eps": 1e-05,
|
| 332 |
"local_attention": 128,
|
|
|
|
| 346 |
"sep_token_id": 50282,
|
| 347 |
"sparse_pred_ignore_index": -100,
|
| 348 |
"sparse_prediction": false,
|
| 349 |
+
"torch_dtype": "float32",
|
| 350 |
+
"transformers_version": "4.52.4",
|
| 351 |
"vocab_size": 50368
|
| 352 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1583962548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5feb2e24a183d2e19efbc21b0cf832c8fa10688dbf7c4f46c0d0ac49a8c48549
|
| 3 |
size 1583962548
|
runs/Sep27_14-16-48_d22a93eda77c/events.out.tfevents.1758982611.d22a93eda77c.63.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a07c99fc7b631fbe60f55bb9c7810eb49327e3d4889c67e709278d98de7dd4f
|
| 3 |
+
size 12637
|
tokenizer_config.json
CHANGED
|
@@ -940,6 +940,6 @@
|
|
| 940 |
"model_max_length": 8192,
|
| 941 |
"pad_token": "[PAD]",
|
| 942 |
"sep_token": "[SEP]",
|
| 943 |
-
"tokenizer_class": "
|
| 944 |
"unk_token": "[UNK]"
|
| 945 |
}
|
|
|
|
| 940 |
"model_max_length": 8192,
|
| 941 |
"pad_token": "[PAD]",
|
| 942 |
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 944 |
"unk_token": "[UNK]"
|
| 945 |
}
|
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:a1cfe353b1d181b3a2a97659bae9a609d172b64bf0c98ed39c4e2d6a124d463a
|
| 3 |
+
size 5304
|