Upload 11 files
Browse files- config.json +671 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +221 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,671 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/ylr/fake-news-detection-main/Roberta/TCMPretrainModel/TCM_Model/TCM_seq_128_roberta_best",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"directionality": "bidi",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6",
|
| 22 |
+
"7": "LABEL_7",
|
| 23 |
+
"8": "LABEL_8",
|
| 24 |
+
"9": "LABEL_9",
|
| 25 |
+
"10": "LABEL_10",
|
| 26 |
+
"11": "LABEL_11",
|
| 27 |
+
"12": "LABEL_12",
|
| 28 |
+
"13": "LABEL_13",
|
| 29 |
+
"14": "LABEL_14",
|
| 30 |
+
"15": "LABEL_15",
|
| 31 |
+
"16": "LABEL_16",
|
| 32 |
+
"17": "LABEL_17",
|
| 33 |
+
"18": "LABEL_18",
|
| 34 |
+
"19": "LABEL_19",
|
| 35 |
+
"20": "LABEL_20",
|
| 36 |
+
"21": "LABEL_21",
|
| 37 |
+
"22": "LABEL_22",
|
| 38 |
+
"23": "LABEL_23",
|
| 39 |
+
"24": "LABEL_24",
|
| 40 |
+
"25": "LABEL_25",
|
| 41 |
+
"26": "LABEL_26",
|
| 42 |
+
"27": "LABEL_27",
|
| 43 |
+
"28": "LABEL_28",
|
| 44 |
+
"29": "LABEL_29",
|
| 45 |
+
"30": "LABEL_30",
|
| 46 |
+
"31": "LABEL_31",
|
| 47 |
+
"32": "LABEL_32",
|
| 48 |
+
"33": "LABEL_33",
|
| 49 |
+
"34": "LABEL_34",
|
| 50 |
+
"35": "LABEL_35",
|
| 51 |
+
"36": "LABEL_36",
|
| 52 |
+
"37": "LABEL_37",
|
| 53 |
+
"38": "LABEL_38",
|
| 54 |
+
"39": "LABEL_39",
|
| 55 |
+
"40": "LABEL_40",
|
| 56 |
+
"41": "LABEL_41",
|
| 57 |
+
"42": "LABEL_42",
|
| 58 |
+
"43": "LABEL_43",
|
| 59 |
+
"44": "LABEL_44",
|
| 60 |
+
"45": "LABEL_45",
|
| 61 |
+
"46": "LABEL_46",
|
| 62 |
+
"47": "LABEL_47",
|
| 63 |
+
"48": "LABEL_48",
|
| 64 |
+
"49": "LABEL_49",
|
| 65 |
+
"50": "LABEL_50",
|
| 66 |
+
"51": "LABEL_51",
|
| 67 |
+
"52": "LABEL_52",
|
| 68 |
+
"53": "LABEL_53",
|
| 69 |
+
"54": "LABEL_54",
|
| 70 |
+
"55": "LABEL_55",
|
| 71 |
+
"56": "LABEL_56",
|
| 72 |
+
"57": "LABEL_57",
|
| 73 |
+
"58": "LABEL_58",
|
| 74 |
+
"59": "LABEL_59",
|
| 75 |
+
"60": "LABEL_60",
|
| 76 |
+
"61": "LABEL_61",
|
| 77 |
+
"62": "LABEL_62",
|
| 78 |
+
"63": "LABEL_63",
|
| 79 |
+
"64": "LABEL_64",
|
| 80 |
+
"65": "LABEL_65",
|
| 81 |
+
"66": "LABEL_66",
|
| 82 |
+
"67": "LABEL_67",
|
| 83 |
+
"68": "LABEL_68",
|
| 84 |
+
"69": "LABEL_69",
|
| 85 |
+
"70": "LABEL_70",
|
| 86 |
+
"71": "LABEL_71",
|
| 87 |
+
"72": "LABEL_72",
|
| 88 |
+
"73": "LABEL_73",
|
| 89 |
+
"74": "LABEL_74",
|
| 90 |
+
"75": "LABEL_75",
|
| 91 |
+
"76": "LABEL_76",
|
| 92 |
+
"77": "LABEL_77",
|
| 93 |
+
"78": "LABEL_78",
|
| 94 |
+
"79": "LABEL_79",
|
| 95 |
+
"80": "LABEL_80",
|
| 96 |
+
"81": "LABEL_81",
|
| 97 |
+
"82": "LABEL_82",
|
| 98 |
+
"83": "LABEL_83",
|
| 99 |
+
"84": "LABEL_84",
|
| 100 |
+
"85": "LABEL_85",
|
| 101 |
+
"86": "LABEL_86",
|
| 102 |
+
"87": "LABEL_87",
|
| 103 |
+
"88": "LABEL_88",
|
| 104 |
+
"89": "LABEL_89",
|
| 105 |
+
"90": "LABEL_90",
|
| 106 |
+
"91": "LABEL_91",
|
| 107 |
+
"92": "LABEL_92",
|
| 108 |
+
"93": "LABEL_93",
|
| 109 |
+
"94": "LABEL_94",
|
| 110 |
+
"95": "LABEL_95",
|
| 111 |
+
"96": "LABEL_96",
|
| 112 |
+
"97": "LABEL_97",
|
| 113 |
+
"98": "LABEL_98",
|
| 114 |
+
"99": "LABEL_99",
|
| 115 |
+
"100": "LABEL_100",
|
| 116 |
+
"101": "LABEL_101",
|
| 117 |
+
"102": "LABEL_102",
|
| 118 |
+
"103": "LABEL_103",
|
| 119 |
+
"104": "LABEL_104",
|
| 120 |
+
"105": "LABEL_105",
|
| 121 |
+
"106": "LABEL_106",
|
| 122 |
+
"107": "LABEL_107",
|
| 123 |
+
"108": "LABEL_108",
|
| 124 |
+
"109": "LABEL_109",
|
| 125 |
+
"110": "LABEL_110",
|
| 126 |
+
"111": "LABEL_111",
|
| 127 |
+
"112": "LABEL_112",
|
| 128 |
+
"113": "LABEL_113",
|
| 129 |
+
"114": "LABEL_114",
|
| 130 |
+
"115": "LABEL_115",
|
| 131 |
+
"116": "LABEL_116",
|
| 132 |
+
"117": "LABEL_117",
|
| 133 |
+
"118": "LABEL_118",
|
| 134 |
+
"119": "LABEL_119",
|
| 135 |
+
"120": "LABEL_120",
|
| 136 |
+
"121": "LABEL_121",
|
| 137 |
+
"122": "LABEL_122",
|
| 138 |
+
"123": "LABEL_123",
|
| 139 |
+
"124": "LABEL_124",
|
| 140 |
+
"125": "LABEL_125",
|
| 141 |
+
"126": "LABEL_126",
|
| 142 |
+
"127": "LABEL_127",
|
| 143 |
+
"128": "LABEL_128",
|
| 144 |
+
"129": "LABEL_129",
|
| 145 |
+
"130": "LABEL_130",
|
| 146 |
+
"131": "LABEL_131",
|
| 147 |
+
"132": "LABEL_132",
|
| 148 |
+
"133": "LABEL_133",
|
| 149 |
+
"134": "LABEL_134",
|
| 150 |
+
"135": "LABEL_135",
|
| 151 |
+
"136": "LABEL_136",
|
| 152 |
+
"137": "LABEL_137",
|
| 153 |
+
"138": "LABEL_138",
|
| 154 |
+
"139": "LABEL_139",
|
| 155 |
+
"140": "LABEL_140",
|
| 156 |
+
"141": "LABEL_141",
|
| 157 |
+
"142": "LABEL_142",
|
| 158 |
+
"143": "LABEL_143",
|
| 159 |
+
"144": "LABEL_144",
|
| 160 |
+
"145": "LABEL_145",
|
| 161 |
+
"146": "LABEL_146",
|
| 162 |
+
"147": "LABEL_147",
|
| 163 |
+
"148": "LABEL_148",
|
| 164 |
+
"149": "LABEL_149",
|
| 165 |
+
"150": "LABEL_150",
|
| 166 |
+
"151": "LABEL_151",
|
| 167 |
+
"152": "LABEL_152",
|
| 168 |
+
"153": "LABEL_153",
|
| 169 |
+
"154": "LABEL_154",
|
| 170 |
+
"155": "LABEL_155",
|
| 171 |
+
"156": "LABEL_156",
|
| 172 |
+
"157": "LABEL_157",
|
| 173 |
+
"158": "LABEL_158",
|
| 174 |
+
"159": "LABEL_159",
|
| 175 |
+
"160": "LABEL_160",
|
| 176 |
+
"161": "LABEL_161",
|
| 177 |
+
"162": "LABEL_162",
|
| 178 |
+
"163": "LABEL_163",
|
| 179 |
+
"164": "LABEL_164",
|
| 180 |
+
"165": "LABEL_165",
|
| 181 |
+
"166": "LABEL_166",
|
| 182 |
+
"167": "LABEL_167",
|
| 183 |
+
"168": "LABEL_168",
|
| 184 |
+
"169": "LABEL_169",
|
| 185 |
+
"170": "LABEL_170",
|
| 186 |
+
"171": "LABEL_171",
|
| 187 |
+
"172": "LABEL_172",
|
| 188 |
+
"173": "LABEL_173",
|
| 189 |
+
"174": "LABEL_174",
|
| 190 |
+
"175": "LABEL_175",
|
| 191 |
+
"176": "LABEL_176",
|
| 192 |
+
"177": "LABEL_177",
|
| 193 |
+
"178": "LABEL_178",
|
| 194 |
+
"179": "LABEL_179",
|
| 195 |
+
"180": "LABEL_180",
|
| 196 |
+
"181": "LABEL_181",
|
| 197 |
+
"182": "LABEL_182",
|
| 198 |
+
"183": "LABEL_183",
|
| 199 |
+
"184": "LABEL_184",
|
| 200 |
+
"185": "LABEL_185",
|
| 201 |
+
"186": "LABEL_186",
|
| 202 |
+
"187": "LABEL_187",
|
| 203 |
+
"188": "LABEL_188",
|
| 204 |
+
"189": "LABEL_189",
|
| 205 |
+
"190": "LABEL_190",
|
| 206 |
+
"191": "LABEL_191",
|
| 207 |
+
"192": "LABEL_192",
|
| 208 |
+
"193": "LABEL_193",
|
| 209 |
+
"194": "LABEL_194",
|
| 210 |
+
"195": "LABEL_195",
|
| 211 |
+
"196": "LABEL_196",
|
| 212 |
+
"197": "LABEL_197",
|
| 213 |
+
"198": "LABEL_198",
|
| 214 |
+
"199": "LABEL_199",
|
| 215 |
+
"200": "LABEL_200",
|
| 216 |
+
"201": "LABEL_201",
|
| 217 |
+
"202": "LABEL_202",
|
| 218 |
+
"203": "LABEL_203",
|
| 219 |
+
"204": "LABEL_204",
|
| 220 |
+
"205": "LABEL_205",
|
| 221 |
+
"206": "LABEL_206",
|
| 222 |
+
"207": "LABEL_207",
|
| 223 |
+
"208": "LABEL_208",
|
| 224 |
+
"209": "LABEL_209",
|
| 225 |
+
"210": "LABEL_210",
|
| 226 |
+
"211": "LABEL_211",
|
| 227 |
+
"212": "LABEL_212",
|
| 228 |
+
"213": "LABEL_213",
|
| 229 |
+
"214": "LABEL_214",
|
| 230 |
+
"215": "LABEL_215",
|
| 231 |
+
"216": "LABEL_216",
|
| 232 |
+
"217": "LABEL_217",
|
| 233 |
+
"218": "LABEL_218",
|
| 234 |
+
"219": "LABEL_219",
|
| 235 |
+
"220": "LABEL_220",
|
| 236 |
+
"221": "LABEL_221",
|
| 237 |
+
"222": "LABEL_222",
|
| 238 |
+
"223": "LABEL_223",
|
| 239 |
+
"224": "LABEL_224",
|
| 240 |
+
"225": "LABEL_225",
|
| 241 |
+
"226": "LABEL_226",
|
| 242 |
+
"227": "LABEL_227",
|
| 243 |
+
"228": "LABEL_228",
|
| 244 |
+
"229": "LABEL_229",
|
| 245 |
+
"230": "LABEL_230",
|
| 246 |
+
"231": "LABEL_231",
|
| 247 |
+
"232": "LABEL_232",
|
| 248 |
+
"233": "LABEL_233",
|
| 249 |
+
"234": "LABEL_234",
|
| 250 |
+
"235": "LABEL_235",
|
| 251 |
+
"236": "LABEL_236",
|
| 252 |
+
"237": "LABEL_237",
|
| 253 |
+
"238": "LABEL_238",
|
| 254 |
+
"239": "LABEL_239",
|
| 255 |
+
"240": "LABEL_240",
|
| 256 |
+
"241": "LABEL_241",
|
| 257 |
+
"242": "LABEL_242",
|
| 258 |
+
"243": "LABEL_243",
|
| 259 |
+
"244": "LABEL_244",
|
| 260 |
+
"245": "LABEL_245",
|
| 261 |
+
"246": "LABEL_246",
|
| 262 |
+
"247": "LABEL_247",
|
| 263 |
+
"248": "LABEL_248",
|
| 264 |
+
"249": "LABEL_249",
|
| 265 |
+
"250": "LABEL_250",
|
| 266 |
+
"251": "LABEL_251",
|
| 267 |
+
"252": "LABEL_252",
|
| 268 |
+
"253": "LABEL_253",
|
| 269 |
+
"254": "LABEL_254",
|
| 270 |
+
"255": "LABEL_255",
|
| 271 |
+
"256": "LABEL_256",
|
| 272 |
+
"257": "LABEL_257",
|
| 273 |
+
"258": "LABEL_258",
|
| 274 |
+
"259": "LABEL_259",
|
| 275 |
+
"260": "LABEL_260",
|
| 276 |
+
"261": "LABEL_261",
|
| 277 |
+
"262": "LABEL_262",
|
| 278 |
+
"263": "LABEL_263",
|
| 279 |
+
"264": "LABEL_264",
|
| 280 |
+
"265": "LABEL_265",
|
| 281 |
+
"266": "LABEL_266",
|
| 282 |
+
"267": "LABEL_267",
|
| 283 |
+
"268": "LABEL_268",
|
| 284 |
+
"269": "LABEL_269",
|
| 285 |
+
"270": "LABEL_270",
|
| 286 |
+
"271": "LABEL_271",
|
| 287 |
+
"272": "LABEL_272",
|
| 288 |
+
"273": "LABEL_273",
|
| 289 |
+
"274": "LABEL_274",
|
| 290 |
+
"275": "LABEL_275",
|
| 291 |
+
"276": "LABEL_276",
|
| 292 |
+
"277": "LABEL_277",
|
| 293 |
+
"278": "LABEL_278",
|
| 294 |
+
"279": "LABEL_279",
|
| 295 |
+
"280": "LABEL_280",
|
| 296 |
+
"281": "LABEL_281",
|
| 297 |
+
"282": "LABEL_282",
|
| 298 |
+
"283": "LABEL_283",
|
| 299 |
+
"284": "LABEL_284",
|
| 300 |
+
"285": "LABEL_285",
|
| 301 |
+
"286": "LABEL_286",
|
| 302 |
+
"287": "LABEL_287",
|
| 303 |
+
"288": "LABEL_288",
|
| 304 |
+
"289": "LABEL_289",
|
| 305 |
+
"290": "LABEL_290",
|
| 306 |
+
"291": "LABEL_291",
|
| 307 |
+
"292": "LABEL_292",
|
| 308 |
+
"293": "LABEL_293",
|
| 309 |
+
"294": "LABEL_294",
|
| 310 |
+
"295": "LABEL_295",
|
| 311 |
+
"296": "LABEL_296",
|
| 312 |
+
"297": "LABEL_297",
|
| 313 |
+
"298": "LABEL_298",
|
| 314 |
+
"299": "LABEL_299",
|
| 315 |
+
"300": "LABEL_300",
|
| 316 |
+
"301": "LABEL_301",
|
| 317 |
+
"302": "LABEL_302",
|
| 318 |
+
"303": "LABEL_303",
|
| 319 |
+
"304": "LABEL_304",
|
| 320 |
+
"305": "LABEL_305",
|
| 321 |
+
"306": "LABEL_306",
|
| 322 |
+
"307": "LABEL_307",
|
| 323 |
+
"308": "LABEL_308",
|
| 324 |
+
"309": "LABEL_309",
|
| 325 |
+
"310": "LABEL_310",
|
| 326 |
+
"311": "LABEL_311",
|
| 327 |
+
"312": "LABEL_312",
|
| 328 |
+
"313": "LABEL_313",
|
| 329 |
+
"314": "LABEL_314",
|
| 330 |
+
"315": "LABEL_315"
|
| 331 |
+
},
|
| 332 |
+
"initializer_range": 0.02,
|
| 333 |
+
"intermediate_size": 4096,
|
| 334 |
+
"label2id": {
|
| 335 |
+
"LABEL_0": 0,
|
| 336 |
+
"LABEL_1": 1,
|
| 337 |
+
"LABEL_10": 10,
|
| 338 |
+
"LABEL_100": 100,
|
| 339 |
+
"LABEL_101": 101,
|
| 340 |
+
"LABEL_102": 102,
|
| 341 |
+
"LABEL_103": 103,
|
| 342 |
+
"LABEL_104": 104,
|
| 343 |
+
"LABEL_105": 105,
|
| 344 |
+
"LABEL_106": 106,
|
| 345 |
+
"LABEL_107": 107,
|
| 346 |
+
"LABEL_108": 108,
|
| 347 |
+
"LABEL_109": 109,
|
| 348 |
+
"LABEL_11": 11,
|
| 349 |
+
"LABEL_110": 110,
|
| 350 |
+
"LABEL_111": 111,
|
| 351 |
+
"LABEL_112": 112,
|
| 352 |
+
"LABEL_113": 113,
|
| 353 |
+
"LABEL_114": 114,
|
| 354 |
+
"LABEL_115": 115,
|
| 355 |
+
"LABEL_116": 116,
|
| 356 |
+
"LABEL_117": 117,
|
| 357 |
+
"LABEL_118": 118,
|
| 358 |
+
"LABEL_119": 119,
|
| 359 |
+
"LABEL_12": 12,
|
| 360 |
+
"LABEL_120": 120,
|
| 361 |
+
"LABEL_121": 121,
|
| 362 |
+
"LABEL_122": 122,
|
| 363 |
+
"LABEL_123": 123,
|
| 364 |
+
"LABEL_124": 124,
|
| 365 |
+
"LABEL_125": 125,
|
| 366 |
+
"LABEL_126": 126,
|
| 367 |
+
"LABEL_127": 127,
|
| 368 |
+
"LABEL_128": 128,
|
| 369 |
+
"LABEL_129": 129,
|
| 370 |
+
"LABEL_13": 13,
|
| 371 |
+
"LABEL_130": 130,
|
| 372 |
+
"LABEL_131": 131,
|
| 373 |
+
"LABEL_132": 132,
|
| 374 |
+
"LABEL_133": 133,
|
| 375 |
+
"LABEL_134": 134,
|
| 376 |
+
"LABEL_135": 135,
|
| 377 |
+
"LABEL_136": 136,
|
| 378 |
+
"LABEL_137": 137,
|
| 379 |
+
"LABEL_138": 138,
|
| 380 |
+
"LABEL_139": 139,
|
| 381 |
+
"LABEL_14": 14,
|
| 382 |
+
"LABEL_140": 140,
|
| 383 |
+
"LABEL_141": 141,
|
| 384 |
+
"LABEL_142": 142,
|
| 385 |
+
"LABEL_143": 143,
|
| 386 |
+
"LABEL_144": 144,
|
| 387 |
+
"LABEL_145": 145,
|
| 388 |
+
"LABEL_146": 146,
|
| 389 |
+
"LABEL_147": 147,
|
| 390 |
+
"LABEL_148": 148,
|
| 391 |
+
"LABEL_149": 149,
|
| 392 |
+
"LABEL_15": 15,
|
| 393 |
+
"LABEL_150": 150,
|
| 394 |
+
"LABEL_151": 151,
|
| 395 |
+
"LABEL_152": 152,
|
| 396 |
+
"LABEL_153": 153,
|
| 397 |
+
"LABEL_154": 154,
|
| 398 |
+
"LABEL_155": 155,
|
| 399 |
+
"LABEL_156": 156,
|
| 400 |
+
"LABEL_157": 157,
|
| 401 |
+
"LABEL_158": 158,
|
| 402 |
+
"LABEL_159": 159,
|
| 403 |
+
"LABEL_16": 16,
|
| 404 |
+
"LABEL_160": 160,
|
| 405 |
+
"LABEL_161": 161,
|
| 406 |
+
"LABEL_162": 162,
|
| 407 |
+
"LABEL_163": 163,
|
| 408 |
+
"LABEL_164": 164,
|
| 409 |
+
"LABEL_165": 165,
|
| 410 |
+
"LABEL_166": 166,
|
| 411 |
+
"LABEL_167": 167,
|
| 412 |
+
"LABEL_168": 168,
|
| 413 |
+
"LABEL_169": 169,
|
| 414 |
+
"LABEL_17": 17,
|
| 415 |
+
"LABEL_170": 170,
|
| 416 |
+
"LABEL_171": 171,
|
| 417 |
+
"LABEL_172": 172,
|
| 418 |
+
"LABEL_173": 173,
|
| 419 |
+
"LABEL_174": 174,
|
| 420 |
+
"LABEL_175": 175,
|
| 421 |
+
"LABEL_176": 176,
|
| 422 |
+
"LABEL_177": 177,
|
| 423 |
+
"LABEL_178": 178,
|
| 424 |
+
"LABEL_179": 179,
|
| 425 |
+
"LABEL_18": 18,
|
| 426 |
+
"LABEL_180": 180,
|
| 427 |
+
"LABEL_181": 181,
|
| 428 |
+
"LABEL_182": 182,
|
| 429 |
+
"LABEL_183": 183,
|
| 430 |
+
"LABEL_184": 184,
|
| 431 |
+
"LABEL_185": 185,
|
| 432 |
+
"LABEL_186": 186,
|
| 433 |
+
"LABEL_187": 187,
|
| 434 |
+
"LABEL_188": 188,
|
| 435 |
+
"LABEL_189": 189,
|
| 436 |
+
"LABEL_19": 19,
|
| 437 |
+
"LABEL_190": 190,
|
| 438 |
+
"LABEL_191": 191,
|
| 439 |
+
"LABEL_192": 192,
|
| 440 |
+
"LABEL_193": 193,
|
| 441 |
+
"LABEL_194": 194,
|
| 442 |
+
"LABEL_195": 195,
|
| 443 |
+
"LABEL_196": 196,
|
| 444 |
+
"LABEL_197": 197,
|
| 445 |
+
"LABEL_198": 198,
|
| 446 |
+
"LABEL_199": 199,
|
| 447 |
+
"LABEL_2": 2,
|
| 448 |
+
"LABEL_20": 20,
|
| 449 |
+
"LABEL_200": 200,
|
| 450 |
+
"LABEL_201": 201,
|
| 451 |
+
"LABEL_202": 202,
|
| 452 |
+
"LABEL_203": 203,
|
| 453 |
+
"LABEL_204": 204,
|
| 454 |
+
"LABEL_205": 205,
|
| 455 |
+
"LABEL_206": 206,
|
| 456 |
+
"LABEL_207": 207,
|
| 457 |
+
"LABEL_208": 208,
|
| 458 |
+
"LABEL_209": 209,
|
| 459 |
+
"LABEL_21": 21,
|
| 460 |
+
"LABEL_210": 210,
|
| 461 |
+
"LABEL_211": 211,
|
| 462 |
+
"LABEL_212": 212,
|
| 463 |
+
"LABEL_213": 213,
|
| 464 |
+
"LABEL_214": 214,
|
| 465 |
+
"LABEL_215": 215,
|
| 466 |
+
"LABEL_216": 216,
|
| 467 |
+
"LABEL_217": 217,
|
| 468 |
+
"LABEL_218": 218,
|
| 469 |
+
"LABEL_219": 219,
|
| 470 |
+
"LABEL_22": 22,
|
| 471 |
+
"LABEL_220": 220,
|
| 472 |
+
"LABEL_221": 221,
|
| 473 |
+
"LABEL_222": 222,
|
| 474 |
+
"LABEL_223": 223,
|
| 475 |
+
"LABEL_224": 224,
|
| 476 |
+
"LABEL_225": 225,
|
| 477 |
+
"LABEL_226": 226,
|
| 478 |
+
"LABEL_227": 227,
|
| 479 |
+
"LABEL_228": 228,
|
| 480 |
+
"LABEL_229": 229,
|
| 481 |
+
"LABEL_23": 23,
|
| 482 |
+
"LABEL_230": 230,
|
| 483 |
+
"LABEL_231": 231,
|
| 484 |
+
"LABEL_232": 232,
|
| 485 |
+
"LABEL_233": 233,
|
| 486 |
+
"LABEL_234": 234,
|
| 487 |
+
"LABEL_235": 235,
|
| 488 |
+
"LABEL_236": 236,
|
| 489 |
+
"LABEL_237": 237,
|
| 490 |
+
"LABEL_238": 238,
|
| 491 |
+
"LABEL_239": 239,
|
| 492 |
+
"LABEL_24": 24,
|
| 493 |
+
"LABEL_240": 240,
|
| 494 |
+
"LABEL_241": 241,
|
| 495 |
+
"LABEL_242": 242,
|
| 496 |
+
"LABEL_243": 243,
|
| 497 |
+
"LABEL_244": 244,
|
| 498 |
+
"LABEL_245": 245,
|
| 499 |
+
"LABEL_246": 246,
|
| 500 |
+
"LABEL_247": 247,
|
| 501 |
+
"LABEL_248": 248,
|
| 502 |
+
"LABEL_249": 249,
|
| 503 |
+
"LABEL_25": 25,
|
| 504 |
+
"LABEL_250": 250,
|
| 505 |
+
"LABEL_251": 251,
|
| 506 |
+
"LABEL_252": 252,
|
| 507 |
+
"LABEL_253": 253,
|
| 508 |
+
"LABEL_254": 254,
|
| 509 |
+
"LABEL_255": 255,
|
| 510 |
+
"LABEL_256": 256,
|
| 511 |
+
"LABEL_257": 257,
|
| 512 |
+
"LABEL_258": 258,
|
| 513 |
+
"LABEL_259": 259,
|
| 514 |
+
"LABEL_26": 26,
|
| 515 |
+
"LABEL_260": 260,
|
| 516 |
+
"LABEL_261": 261,
|
| 517 |
+
"LABEL_262": 262,
|
| 518 |
+
"LABEL_263": 263,
|
| 519 |
+
"LABEL_264": 264,
|
| 520 |
+
"LABEL_265": 265,
|
| 521 |
+
"LABEL_266": 266,
|
| 522 |
+
"LABEL_267": 267,
|
| 523 |
+
"LABEL_268": 268,
|
| 524 |
+
"LABEL_269": 269,
|
| 525 |
+
"LABEL_27": 27,
|
| 526 |
+
"LABEL_270": 270,
|
| 527 |
+
"LABEL_271": 271,
|
| 528 |
+
"LABEL_272": 272,
|
| 529 |
+
"LABEL_273": 273,
|
| 530 |
+
"LABEL_274": 274,
|
| 531 |
+
"LABEL_275": 275,
|
| 532 |
+
"LABEL_276": 276,
|
| 533 |
+
"LABEL_277": 277,
|
| 534 |
+
"LABEL_278": 278,
|
| 535 |
+
"LABEL_279": 279,
|
| 536 |
+
"LABEL_28": 28,
|
| 537 |
+
"LABEL_280": 280,
|
| 538 |
+
"LABEL_281": 281,
|
| 539 |
+
"LABEL_282": 282,
|
| 540 |
+
"LABEL_283": 283,
|
| 541 |
+
"LABEL_284": 284,
|
| 542 |
+
"LABEL_285": 285,
|
| 543 |
+
"LABEL_286": 286,
|
| 544 |
+
"LABEL_287": 287,
|
| 545 |
+
"LABEL_288": 288,
|
| 546 |
+
"LABEL_289": 289,
|
| 547 |
+
"LABEL_29": 29,
|
| 548 |
+
"LABEL_290": 290,
|
| 549 |
+
"LABEL_291": 291,
|
| 550 |
+
"LABEL_292": 292,
|
| 551 |
+
"LABEL_293": 293,
|
| 552 |
+
"LABEL_294": 294,
|
| 553 |
+
"LABEL_295": 295,
|
| 554 |
+
"LABEL_296": 296,
|
| 555 |
+
"LABEL_297": 297,
|
| 556 |
+
"LABEL_298": 298,
|
| 557 |
+
"LABEL_299": 299,
|
| 558 |
+
"LABEL_3": 3,
|
| 559 |
+
"LABEL_30": 30,
|
| 560 |
+
"LABEL_300": 300,
|
| 561 |
+
"LABEL_301": 301,
|
| 562 |
+
"LABEL_302": 302,
|
| 563 |
+
"LABEL_303": 303,
|
| 564 |
+
"LABEL_304": 304,
|
| 565 |
+
"LABEL_305": 305,
|
| 566 |
+
"LABEL_306": 306,
|
| 567 |
+
"LABEL_307": 307,
|
| 568 |
+
"LABEL_308": 308,
|
| 569 |
+
"LABEL_309": 309,
|
| 570 |
+
"LABEL_31": 31,
|
| 571 |
+
"LABEL_310": 310,
|
| 572 |
+
"LABEL_311": 311,
|
| 573 |
+
"LABEL_312": 312,
|
| 574 |
+
"LABEL_313": 313,
|
| 575 |
+
"LABEL_314": 314,
|
| 576 |
+
"LABEL_315": 315,
|
| 577 |
+
"LABEL_32": 32,
|
| 578 |
+
"LABEL_33": 33,
|
| 579 |
+
"LABEL_34": 34,
|
| 580 |
+
"LABEL_35": 35,
|
| 581 |
+
"LABEL_36": 36,
|
| 582 |
+
"LABEL_37": 37,
|
| 583 |
+
"LABEL_38": 38,
|
| 584 |
+
"LABEL_39": 39,
|
| 585 |
+
"LABEL_4": 4,
|
| 586 |
+
"LABEL_40": 40,
|
| 587 |
+
"LABEL_41": 41,
|
| 588 |
+
"LABEL_42": 42,
|
| 589 |
+
"LABEL_43": 43,
|
| 590 |
+
"LABEL_44": 44,
|
| 591 |
+
"LABEL_45": 45,
|
| 592 |
+
"LABEL_46": 46,
|
| 593 |
+
"LABEL_47": 47,
|
| 594 |
+
"LABEL_48": 48,
|
| 595 |
+
"LABEL_49": 49,
|
| 596 |
+
"LABEL_5": 5,
|
| 597 |
+
"LABEL_50": 50,
|
| 598 |
+
"LABEL_51": 51,
|
| 599 |
+
"LABEL_52": 52,
|
| 600 |
+
"LABEL_53": 53,
|
| 601 |
+
"LABEL_54": 54,
|
| 602 |
+
"LABEL_55": 55,
|
| 603 |
+
"LABEL_56": 56,
|
| 604 |
+
"LABEL_57": 57,
|
| 605 |
+
"LABEL_58": 58,
|
| 606 |
+
"LABEL_59": 59,
|
| 607 |
+
"LABEL_6": 6,
|
| 608 |
+
"LABEL_60": 60,
|
| 609 |
+
"LABEL_61": 61,
|
| 610 |
+
"LABEL_62": 62,
|
| 611 |
+
"LABEL_63": 63,
|
| 612 |
+
"LABEL_64": 64,
|
| 613 |
+
"LABEL_65": 65,
|
| 614 |
+
"LABEL_66": 66,
|
| 615 |
+
"LABEL_67": 67,
|
| 616 |
+
"LABEL_68": 68,
|
| 617 |
+
"LABEL_69": 69,
|
| 618 |
+
"LABEL_7": 7,
|
| 619 |
+
"LABEL_70": 70,
|
| 620 |
+
"LABEL_71": 71,
|
| 621 |
+
"LABEL_72": 72,
|
| 622 |
+
"LABEL_73": 73,
|
| 623 |
+
"LABEL_74": 74,
|
| 624 |
+
"LABEL_75": 75,
|
| 625 |
+
"LABEL_76": 76,
|
| 626 |
+
"LABEL_77": 77,
|
| 627 |
+
"LABEL_78": 78,
|
| 628 |
+
"LABEL_79": 79,
|
| 629 |
+
"LABEL_8": 8,
|
| 630 |
+
"LABEL_80": 80,
|
| 631 |
+
"LABEL_81": 81,
|
| 632 |
+
"LABEL_82": 82,
|
| 633 |
+
"LABEL_83": 83,
|
| 634 |
+
"LABEL_84": 84,
|
| 635 |
+
"LABEL_85": 85,
|
| 636 |
+
"LABEL_86": 86,
|
| 637 |
+
"LABEL_87": 87,
|
| 638 |
+
"LABEL_88": 88,
|
| 639 |
+
"LABEL_89": 89,
|
| 640 |
+
"LABEL_9": 9,
|
| 641 |
+
"LABEL_90": 90,
|
| 642 |
+
"LABEL_91": 91,
|
| 643 |
+
"LABEL_92": 92,
|
| 644 |
+
"LABEL_93": 93,
|
| 645 |
+
"LABEL_94": 94,
|
| 646 |
+
"LABEL_95": 95,
|
| 647 |
+
"LABEL_96": 96,
|
| 648 |
+
"LABEL_97": 97,
|
| 649 |
+
"LABEL_98": 98,
|
| 650 |
+
"LABEL_99": 99
|
| 651 |
+
},
|
| 652 |
+
"layer_norm_eps": 1e-12,
|
| 653 |
+
"max_position_embeddings": 512,
|
| 654 |
+
"model_type": "bert",
|
| 655 |
+
"num_attention_heads": 16,
|
| 656 |
+
"num_hidden_layers": 24,
|
| 657 |
+
"output_past": true,
|
| 658 |
+
"pad_token_id": 0,
|
| 659 |
+
"pooler_fc_size": 768,
|
| 660 |
+
"pooler_num_attention_heads": 12,
|
| 661 |
+
"pooler_num_fc_layers": 3,
|
| 662 |
+
"pooler_size_per_head": 128,
|
| 663 |
+
"pooler_type": "first_token_transform",
|
| 664 |
+
"position_embedding_type": "absolute",
|
| 665 |
+
"problem_type": "single_label_classification",
|
| 666 |
+
"torch_dtype": "float32",
|
| 667 |
+
"transformers_version": "4.45.1",
|
| 668 |
+
"type_vocab_size": 2,
|
| 669 |
+
"use_cache": true,
|
| 670 |
+
"vocab_size": 21128
|
| 671 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32f9a4cc8299182e4176acc188deda1e8dc72321015a249da2d635fc79a11a63
|
| 3 |
+
size 1303432304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af28854f94d3785f90a2371e960d098badbf0797044a63989730b0e65dd5da20
|
| 3 |
+
size 2607099501
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e325853bf91e09a74afbc9e938226a89bcd26e9b14bab16cd33b7cc206bc2429
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1135d2f86d99f58027d78e2fa5abd2931418821fe4bdd3920a4b50c8a2af571f
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8715846994535519,
|
| 3 |
+
"best_model_checkpoint": "./neikexue_V2_seq_128__1e-5_model_results/checkpoint-2000",
|
| 4 |
+
"epoch": 17.391304347826086,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8695652173913043,
|
| 13 |
+
"grad_norm": 8.864755630493164,
|
| 14 |
+
"learning_rate": 9.710144927536233e-06,
|
| 15 |
+
"loss": 5.6733,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.7391304347826086,
|
| 20 |
+
"grad_norm": 9.545233726501465,
|
| 21 |
+
"learning_rate": 9.420289855072464e-06,
|
| 22 |
+
"loss": 5.0217,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.608695652173913,
|
| 27 |
+
"grad_norm": 10.265801429748535,
|
| 28 |
+
"learning_rate": 9.130434782608697e-06,
|
| 29 |
+
"loss": 4.3971,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.4782608695652173,
|
| 34 |
+
"grad_norm": 10.584877014160156,
|
| 35 |
+
"learning_rate": 8.840579710144929e-06,
|
| 36 |
+
"loss": 3.8406,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.3478260869565215,
|
| 41 |
+
"grad_norm": 11.208259582519531,
|
| 42 |
+
"learning_rate": 8.55072463768116e-06,
|
| 43 |
+
"loss": 3.3202,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.3478260869565215,
|
| 48 |
+
"eval_accuracy": 0.592896174863388,
|
| 49 |
+
"eval_f1": 0.5088359121146007,
|
| 50 |
+
"eval_loss": 3.198462724685669,
|
| 51 |
+
"eval_precision": 0.48192588377014606,
|
| 52 |
+
"eval_recall": 0.592896174863388,
|
| 53 |
+
"eval_runtime": 0.893,
|
| 54 |
+
"eval_samples_per_second": 409.855,
|
| 55 |
+
"eval_steps_per_second": 25.756,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.217391304347826,
|
| 60 |
+
"grad_norm": 10.305059432983398,
|
| 61 |
+
"learning_rate": 8.260869565217392e-06,
|
| 62 |
+
"loss": 2.9294,
|
| 63 |
+
"step": 600
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.086956521739131,
|
| 67 |
+
"grad_norm": 9.287023544311523,
|
| 68 |
+
"learning_rate": 7.971014492753623e-06,
|
| 69 |
+
"loss": 2.4987,
|
| 70 |
+
"step": 700
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.956521739130435,
|
| 74 |
+
"grad_norm": 8.611043930053711,
|
| 75 |
+
"learning_rate": 7.681159420289856e-06,
|
| 76 |
+
"loss": 2.1443,
|
| 77 |
+
"step": 800
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.826086956521739,
|
| 81 |
+
"grad_norm": 9.929250717163086,
|
| 82 |
+
"learning_rate": 7.391304347826087e-06,
|
| 83 |
+
"loss": 1.8154,
|
| 84 |
+
"step": 900
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 8.695652173913043,
|
| 88 |
+
"grad_norm": 8.795051574707031,
|
| 89 |
+
"learning_rate": 7.10144927536232e-06,
|
| 90 |
+
"loss": 1.537,
|
| 91 |
+
"step": 1000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 8.695652173913043,
|
| 95 |
+
"eval_accuracy": 0.825136612021858,
|
| 96 |
+
"eval_f1": 0.7840855865446029,
|
| 97 |
+
"eval_loss": 1.8385679721832275,
|
| 98 |
+
"eval_precision": 0.7657364038511579,
|
| 99 |
+
"eval_recall": 0.825136612021858,
|
| 100 |
+
"eval_runtime": 0.8634,
|
| 101 |
+
"eval_samples_per_second": 423.891,
|
| 102 |
+
"eval_steps_per_second": 26.638,
|
| 103 |
+
"step": 1000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 9.565217391304348,
|
| 107 |
+
"grad_norm": 6.896790981292725,
|
| 108 |
+
"learning_rate": 6.811594202898551e-06,
|
| 109 |
+
"loss": 1.3088,
|
| 110 |
+
"step": 1100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 10.434782608695652,
|
| 114 |
+
"grad_norm": 7.9147725105285645,
|
| 115 |
+
"learning_rate": 6.521739130434783e-06,
|
| 116 |
+
"loss": 1.0947,
|
| 117 |
+
"step": 1200
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 11.304347826086957,
|
| 121 |
+
"grad_norm": 6.530330181121826,
|
| 122 |
+
"learning_rate": 6.2318840579710145e-06,
|
| 123 |
+
"loss": 0.9349,
|
| 124 |
+
"step": 1300
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 12.173913043478262,
|
| 128 |
+
"grad_norm": 6.054310321807861,
|
| 129 |
+
"learning_rate": 5.942028985507247e-06,
|
| 130 |
+
"loss": 0.773,
|
| 131 |
+
"step": 1400
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 13.043478260869565,
|
| 135 |
+
"grad_norm": 5.687331199645996,
|
| 136 |
+
"learning_rate": 5.652173913043479e-06,
|
| 137 |
+
"loss": 0.6669,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 13.043478260869565,
|
| 142 |
+
"eval_accuracy": 0.8497267759562842,
|
| 143 |
+
"eval_f1": 0.8189744833187457,
|
| 144 |
+
"eval_loss": 1.1578365564346313,
|
| 145 |
+
"eval_precision": 0.8049635701275045,
|
| 146 |
+
"eval_recall": 0.8497267759562842,
|
| 147 |
+
"eval_runtime": 0.9265,
|
| 148 |
+
"eval_samples_per_second": 395.024,
|
| 149 |
+
"eval_steps_per_second": 24.824,
|
| 150 |
+
"step": 1500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 13.91304347826087,
|
| 154 |
+
"grad_norm": 4.295091152191162,
|
| 155 |
+
"learning_rate": 5.362318840579711e-06,
|
| 156 |
+
"loss": 0.5477,
|
| 157 |
+
"step": 1600
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 14.782608695652174,
|
| 161 |
+
"grad_norm": 3.5699689388275146,
|
| 162 |
+
"learning_rate": 5.072463768115943e-06,
|
| 163 |
+
"loss": 0.4643,
|
| 164 |
+
"step": 1700
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 15.652173913043478,
|
| 168 |
+
"grad_norm": 3.011284828186035,
|
| 169 |
+
"learning_rate": 4.782608695652174e-06,
|
| 170 |
+
"loss": 0.3989,
|
| 171 |
+
"step": 1800
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 16.52173913043478,
|
| 175 |
+
"grad_norm": 2.8458871841430664,
|
| 176 |
+
"learning_rate": 4.492753623188406e-06,
|
| 177 |
+
"loss": 0.3407,
|
| 178 |
+
"step": 1900
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 17.391304347826086,
|
| 182 |
+
"grad_norm": 2.9610633850097656,
|
| 183 |
+
"learning_rate": 4.202898550724638e-06,
|
| 184 |
+
"loss": 0.2911,
|
| 185 |
+
"step": 2000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 17.391304347826086,
|
| 189 |
+
"eval_accuracy": 0.8715846994535519,
|
| 190 |
+
"eval_f1": 0.8439289459781263,
|
| 191 |
+
"eval_loss": 0.836195170879364,
|
| 192 |
+
"eval_precision": 0.8367486338797814,
|
| 193 |
+
"eval_recall": 0.8715846994535519,
|
| 194 |
+
"eval_runtime": 1.0977,
|
| 195 |
+
"eval_samples_per_second": 333.42,
|
| 196 |
+
"eval_steps_per_second": 20.953,
|
| 197 |
+
"step": 2000
|
| 198 |
+
}
|
| 199 |
+
],
|
| 200 |
+
"logging_steps": 100,
|
| 201 |
+
"max_steps": 3450,
|
| 202 |
+
"num_input_tokens_seen": 0,
|
| 203 |
+
"num_train_epochs": 30,
|
| 204 |
+
"save_steps": 500,
|
| 205 |
+
"stateful_callbacks": {
|
| 206 |
+
"TrainerControl": {
|
| 207 |
+
"args": {
|
| 208 |
+
"should_epoch_stop": false,
|
| 209 |
+
"should_evaluate": false,
|
| 210 |
+
"should_log": false,
|
| 211 |
+
"should_save": true,
|
| 212 |
+
"should_training_stop": false
|
| 213 |
+
},
|
| 214 |
+
"attributes": {}
|
| 215 |
+
}
|
| 216 |
+
},
|
| 217 |
+
"total_flos": 7423711588546560.0,
|
| 218 |
+
"train_batch_size": 16,
|
| 219 |
+
"trial_name": null,
|
| 220 |
+
"trial_params": null
|
| 221 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e80655d9a80c717c27a2bb0296d16298462cccd87aef57f9108318b564f8ad7
|
| 3 |
+
size 5240
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|