🔄 Incremental correlations | F1µ: 0.000, Hamming: 0.936
Browse files- README.md +5 -5
- checkpoint-35/config.json +132 -251
- checkpoint-35/model.safetensors +1 -1
- checkpoint-35/special_tokens_map.json +35 -5
- checkpoint-35/tokenizer_config.json +7 -0
- checkpoint-35/trainer_state.json +12 -12
- config.json +8 -133
- model.safetensors +1 -1
- special_tokens_map.json +35 -5
- tokenizer_config.json +7 -0
README.md
CHANGED
|
@@ -21,23 +21,23 @@ Fine-tuned FinBERT model for financial correlations analysis in TradePulse.
|
|
| 21 |
|
| 22 |
## Performance
|
| 23 |
|
| 24 |
-
*Last training: 2025-07-25 12:
|
| 25 |
*Dataset: `news_20250725.csv` (138 samples)*
|
| 26 |
|
| 27 |
| Metric | Value |
|
| 28 |
|--------|-------|
|
| 29 |
-
| Loss | 0.
|
| 30 |
| Subset Accuracy | 0.0000 |
|
| 31 |
| F1 Score | 0.0000 |
|
| 32 |
| F1 Micro | 0.0000 |
|
| 33 |
| F1 Macro | 0.0000 |
|
| 34 |
-
| Hamming Score | 0.
|
| 35 |
| Precision | 0.0000 |
|
| 36 |
| Recall | 0.0000 |
|
| 37 |
|
| 38 |
## Training Details
|
| 39 |
|
| 40 |
-
- **Base Model**:
|
| 41 |
- **Training Mode**: Incremental
|
| 42 |
- **Epochs**: 2
|
| 43 |
- **Learning Rate**: 1e-05
|
|
@@ -65,4 +65,4 @@ predictions = torch.sigmoid(outputs.logits).squeeze() > 0.5
|
|
| 65 |
## Model Card Authors
|
| 66 |
|
| 67 |
- TradePulse ML Team
|
| 68 |
-
- Auto-generated on 2025-07-25 12:
|
|
|
|
| 21 |
|
| 22 |
## Performance
|
| 23 |
|
| 24 |
+
*Last training: 2025-07-25 12:58*
|
| 25 |
*Dataset: `news_20250725.csv` (138 samples)*
|
| 26 |
|
| 27 |
| Metric | Value |
|
| 28 |
|--------|-------|
|
| 29 |
+
| Loss | 0.4966 |
|
| 30 |
| Subset Accuracy | 0.0000 |
|
| 31 |
| F1 Score | 0.0000 |
|
| 32 |
| F1 Micro | 0.0000 |
|
| 33 |
| F1 Macro | 0.0000 |
|
| 34 |
+
| Hamming Score | 0.9280 |
|
| 35 |
| Precision | 0.0000 |
|
| 36 |
| Recall | 0.0000 |
|
| 37 |
|
| 38 |
## Training Details
|
| 39 |
|
| 40 |
+
- **Base Model**: Bencode92/tradepulse-finbert-correlations
|
| 41 |
- **Training Mode**: Incremental
|
| 42 |
- **Epochs**: 2
|
| 43 |
- **Learning Rate**: 1e-05
|
|
|
|
| 65 |
## Model Card Authors
|
| 66 |
|
| 67 |
- TradePulse ML Team
|
| 68 |
+
- Auto-generated on 2025-07-25 12:58:23
|
checkpoint-35/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
|
@@ -9,260 +9,141 @@
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "
|
| 29 |
-
"17": "
|
| 30 |
-
"18": "
|
| 31 |
-
"19": "
|
| 32 |
-
"20": "
|
| 33 |
-
"21": "
|
| 34 |
-
"22": "
|
| 35 |
-
"23": "
|
| 36 |
-
"24": "
|
| 37 |
-
"25": "
|
| 38 |
-
"26": "
|
| 39 |
-
"27": "
|
| 40 |
-
"28": "
|
| 41 |
-
"29": "
|
| 42 |
-
"30": "
|
| 43 |
-
"31": "
|
| 44 |
-
"32": "
|
| 45 |
-
"33": "
|
| 46 |
-
"34": "
|
| 47 |
-
"35": "
|
| 48 |
-
"36": "
|
| 49 |
-
"37": "
|
| 50 |
-
"38": "
|
| 51 |
-
"39": "
|
| 52 |
-
"40": "
|
| 53 |
-
"41": "
|
| 54 |
-
"42": "
|
| 55 |
-
"43": "
|
| 56 |
-
"44": "
|
| 57 |
-
"45": "
|
| 58 |
-
"46": "
|
| 59 |
-
"47": "
|
| 60 |
-
"48": "
|
| 61 |
-
"49": "
|
| 62 |
-
"50": "
|
| 63 |
-
"51": "
|
| 64 |
-
"52": "
|
| 65 |
-
"53": "
|
| 66 |
-
"54": "
|
| 67 |
-
"55": "
|
| 68 |
-
"56": "
|
| 69 |
-
"57": "
|
| 70 |
-
"58": "
|
| 71 |
-
"59": "
|
| 72 |
-
"60": "
|
| 73 |
-
"61": "
|
| 74 |
-
"62": "
|
| 75 |
-
"63": "
|
| 76 |
-
"64": "
|
| 77 |
-
"65": "
|
| 78 |
-
"66": "
|
| 79 |
-
"67": "
|
| 80 |
-
"68": "
|
| 81 |
-
"69": "
|
| 82 |
-
"70": "
|
| 83 |
-
"71": "
|
| 84 |
-
"72": "
|
| 85 |
-
"73": "
|
| 86 |
-
"74": "
|
| 87 |
-
"75": "
|
| 88 |
-
"76": "
|
| 89 |
-
"77": "
|
| 90 |
-
"78": "
|
| 91 |
-
"79": "
|
| 92 |
-
"80": "
|
| 93 |
-
"81": "
|
| 94 |
-
"82": "
|
| 95 |
-
"83": "
|
| 96 |
-
"84": "
|
| 97 |
-
"85": "
|
| 98 |
-
"86": "
|
| 99 |
-
"87": "
|
| 100 |
-
"88": "
|
| 101 |
-
"89": "
|
| 102 |
-
"90": "
|
| 103 |
-
"91": "
|
| 104 |
-
"92": "
|
| 105 |
-
"93": "
|
| 106 |
-
"94": "
|
| 107 |
-
"95": "
|
| 108 |
-
"96": "
|
| 109 |
-
"97": "
|
| 110 |
-
"98": "
|
| 111 |
-
"99": "
|
| 112 |
-
"100": "
|
| 113 |
-
"101": "
|
| 114 |
-
"102": "
|
| 115 |
-
"103": "
|
| 116 |
-
"104": "
|
| 117 |
-
"105": "
|
| 118 |
-
"106": "
|
| 119 |
-
"107": "
|
| 120 |
-
"108": "
|
| 121 |
-
"109": "
|
| 122 |
-
"110": "
|
| 123 |
-
"111": "
|
| 124 |
-
"112": "
|
| 125 |
-
"113": "
|
| 126 |
-
"114": "
|
| 127 |
-
"115": "
|
| 128 |
-
"116": "
|
| 129 |
-
"117": "
|
| 130 |
-
"118": "
|
| 131 |
-
"119": "
|
| 132 |
-
"120": "
|
| 133 |
-
"121": "
|
| 134 |
-
"122": "
|
| 135 |
-
"123": "
|
| 136 |
-
"124": "
|
| 137 |
},
|
| 138 |
"initializer_range": 0.02,
|
| 139 |
"intermediate_size": 3072,
|
| 140 |
"label2id": {
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"LABEL_103": 103,
|
| 148 |
-
"LABEL_104": 104,
|
| 149 |
-
"LABEL_105": 105,
|
| 150 |
-
"LABEL_106": 106,
|
| 151 |
-
"LABEL_107": 107,
|
| 152 |
-
"LABEL_108": 108,
|
| 153 |
-
"LABEL_109": 109,
|
| 154 |
-
"LABEL_11": 11,
|
| 155 |
-
"LABEL_110": 110,
|
| 156 |
-
"LABEL_111": 111,
|
| 157 |
-
"LABEL_112": 112,
|
| 158 |
-
"LABEL_113": 113,
|
| 159 |
-
"LABEL_114": 114,
|
| 160 |
-
"LABEL_115": 115,
|
| 161 |
-
"LABEL_116": 116,
|
| 162 |
-
"LABEL_117": 117,
|
| 163 |
-
"LABEL_118": 118,
|
| 164 |
-
"LABEL_119": 119,
|
| 165 |
-
"LABEL_12": 12,
|
| 166 |
-
"LABEL_120": 120,
|
| 167 |
-
"LABEL_121": 121,
|
| 168 |
-
"LABEL_122": 122,
|
| 169 |
-
"LABEL_123": 123,
|
| 170 |
-
"LABEL_124": 124,
|
| 171 |
-
"LABEL_13": 13,
|
| 172 |
-
"LABEL_14": 14,
|
| 173 |
-
"LABEL_15": 15,
|
| 174 |
-
"LABEL_16": 16,
|
| 175 |
-
"LABEL_17": 17,
|
| 176 |
-
"LABEL_18": 18,
|
| 177 |
-
"LABEL_19": 19,
|
| 178 |
-
"LABEL_2": 2,
|
| 179 |
-
"LABEL_20": 20,
|
| 180 |
-
"LABEL_21": 21,
|
| 181 |
-
"LABEL_22": 22,
|
| 182 |
-
"LABEL_23": 23,
|
| 183 |
-
"LABEL_24": 24,
|
| 184 |
-
"LABEL_25": 25,
|
| 185 |
-
"LABEL_26": 26,
|
| 186 |
-
"LABEL_27": 27,
|
| 187 |
-
"LABEL_28": 28,
|
| 188 |
-
"LABEL_29": 29,
|
| 189 |
-
"LABEL_3": 3,
|
| 190 |
-
"LABEL_30": 30,
|
| 191 |
-
"LABEL_31": 31,
|
| 192 |
-
"LABEL_32": 32,
|
| 193 |
-
"LABEL_33": 33,
|
| 194 |
-
"LABEL_34": 34,
|
| 195 |
-
"LABEL_35": 35,
|
| 196 |
-
"LABEL_36": 36,
|
| 197 |
-
"LABEL_37": 37,
|
| 198 |
-
"LABEL_38": 38,
|
| 199 |
-
"LABEL_39": 39,
|
| 200 |
-
"LABEL_4": 4,
|
| 201 |
-
"LABEL_40": 40,
|
| 202 |
-
"LABEL_41": 41,
|
| 203 |
-
"LABEL_42": 42,
|
| 204 |
-
"LABEL_43": 43,
|
| 205 |
-
"LABEL_44": 44,
|
| 206 |
-
"LABEL_45": 45,
|
| 207 |
-
"LABEL_46": 46,
|
| 208 |
-
"LABEL_47": 47,
|
| 209 |
-
"LABEL_48": 48,
|
| 210 |
-
"LABEL_49": 49,
|
| 211 |
-
"LABEL_5": 5,
|
| 212 |
-
"LABEL_50": 50,
|
| 213 |
-
"LABEL_51": 51,
|
| 214 |
-
"LABEL_52": 52,
|
| 215 |
-
"LABEL_53": 53,
|
| 216 |
-
"LABEL_54": 54,
|
| 217 |
-
"LABEL_55": 55,
|
| 218 |
-
"LABEL_56": 56,
|
| 219 |
-
"LABEL_57": 57,
|
| 220 |
-
"LABEL_58": 58,
|
| 221 |
-
"LABEL_59": 59,
|
| 222 |
-
"LABEL_6": 6,
|
| 223 |
-
"LABEL_60": 60,
|
| 224 |
-
"LABEL_61": 61,
|
| 225 |
-
"LABEL_62": 62,
|
| 226 |
-
"LABEL_63": 63,
|
| 227 |
-
"LABEL_64": 64,
|
| 228 |
-
"LABEL_65": 65,
|
| 229 |
-
"LABEL_66": 66,
|
| 230 |
-
"LABEL_67": 67,
|
| 231 |
-
"LABEL_68": 68,
|
| 232 |
-
"LABEL_69": 69,
|
| 233 |
-
"LABEL_7": 7,
|
| 234 |
-
"LABEL_70": 70,
|
| 235 |
-
"LABEL_71": 71,
|
| 236 |
-
"LABEL_72": 72,
|
| 237 |
-
"LABEL_73": 73,
|
| 238 |
-
"LABEL_74": 74,
|
| 239 |
-
"LABEL_75": 75,
|
| 240 |
-
"LABEL_76": 76,
|
| 241 |
-
"LABEL_77": 77,
|
| 242 |
-
"LABEL_78": 78,
|
| 243 |
-
"LABEL_79": 79,
|
| 244 |
-
"LABEL_8": 8,
|
| 245 |
-
"LABEL_80": 80,
|
| 246 |
-
"LABEL_81": 81,
|
| 247 |
-
"LABEL_82": 82,
|
| 248 |
-
"LABEL_83": 83,
|
| 249 |
-
"LABEL_84": 84,
|
| 250 |
-
"LABEL_85": 85,
|
| 251 |
-
"LABEL_86": 86,
|
| 252 |
-
"LABEL_87": 87,
|
| 253 |
-
"LABEL_88": 88,
|
| 254 |
-
"LABEL_89": 89,
|
| 255 |
-
"LABEL_9": 9,
|
| 256 |
-
"LABEL_90": 90,
|
| 257 |
-
"LABEL_91": 91,
|
| 258 |
-
"LABEL_92": 92,
|
| 259 |
-
"LABEL_93": 93,
|
| 260 |
-
"LABEL_94": 94,
|
| 261 |
-
"LABEL_95": 95,
|
| 262 |
-
"LABEL_96": 96,
|
| 263 |
-
"LABEL_97": 97,
|
| 264 |
-
"LABEL_98": 98,
|
| 265 |
-
"LABEL_99": 99
|
| 266 |
},
|
| 267 |
"layer_norm_eps": 1e-12,
|
| 268 |
"max_position_embeddings": 512,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Bencode92/tradepulse-finbert-correlations",
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "AE:DIAMONDS",
|
| 13 |
+
"1": "AE:PETROLEUM_CRUDE",
|
| 14 |
+
"2": "AR:CORN",
|
| 15 |
+
"3": "AU:ALUMINIUM_ORE",
|
| 16 |
+
"4": "AU:COAL",
|
| 17 |
+
"5": "AU:IRON_ORE",
|
| 18 |
+
"6": "AU:NATGAS",
|
| 19 |
+
"7": "AU:WHEAT",
|
| 20 |
+
"8": "AU:ZINC_ORE",
|
| 21 |
+
"9": "BE:ZINC_METAL",
|
| 22 |
+
"10": "BO:ZINC_ORE",
|
| 23 |
+
"11": "BR:COFFEE",
|
| 24 |
+
"12": "BR:CORN",
|
| 25 |
+
"13": "BR:IRON_ORE",
|
| 26 |
+
"14": "BR:MEAT",
|
| 27 |
+
"15": "BR:SOYBEAN",
|
| 28 |
+
"16": "BR:SUGAR",
|
| 29 |
+
"17": "CA:ALUMINIUM_METAL",
|
| 30 |
+
"18": "CA:NICKEL_METAL",
|
| 31 |
+
"19": "CA:WHEAT",
|
| 32 |
+
"20": "CD:COPPER_REFINED",
|
| 33 |
+
"21": "CH:GOLD",
|
| 34 |
+
"22": "CH:PHARMACEUTICALS",
|
| 35 |
+
"23": "CL:COPPER_ORE",
|
| 36 |
+
"24": "CL:COPPER_REFINED",
|
| 37 |
+
"25": "CL:COPPER_UNREFINED",
|
| 38 |
+
"26": "CN:APPAREL",
|
| 39 |
+
"27": "CN:CARBON",
|
| 40 |
+
"28": "CN:CHEMICALS_MISC",
|
| 41 |
+
"29": "CN:CHEMICALS_ORGANIC",
|
| 42 |
+
"30": "CN:ELECTRICAL_MACHINERY",
|
| 43 |
+
"31": "CN:FURNITURE",
|
| 44 |
+
"32": "CN:MACHINERY",
|
| 45 |
+
"33": "CN:NICKEL_METAL",
|
| 46 |
+
"34": "CN:OPTICAL_INSTRUMENTS",
|
| 47 |
+
"35": "CN:PAPER",
|
| 48 |
+
"36": "CN:PLASTICS",
|
| 49 |
+
"37": "CN:RARE_GASES",
|
| 50 |
+
"38": "CN:RUBBER",
|
| 51 |
+
"39": "CN:SHIPS",
|
| 52 |
+
"40": "CN:SILVER",
|
| 53 |
+
"41": "CN:TOYS",
|
| 54 |
+
"42": "CN:VEHICLES",
|
| 55 |
+
"43": "CN:WOOD",
|
| 56 |
+
"44": "DE:AIRCRAFT",
|
| 57 |
+
"45": "DE:CHEMICALS_MISC",
|
| 58 |
+
"46": "DE:COCOA",
|
| 59 |
+
"47": "DE:FINANCIAL_SERVICES",
|
| 60 |
+
"48": "DE:OPTICAL_INSTRUMENTS",
|
| 61 |
+
"49": "DE:PAPER",
|
| 62 |
+
"50": "DE:PHARMACEUTICALS",
|
| 63 |
+
"51": "DE:RARE_GASES",
|
| 64 |
+
"52": "DE:VEHICLES",
|
| 65 |
+
"53": "FI:NICKEL_ORE",
|
| 66 |
+
"54": "FR:AIRCRAFT",
|
| 67 |
+
"55": "FR:BEVERAGES",
|
| 68 |
+
"56": "FR:COSMETICS",
|
| 69 |
+
"57": "FR:ELECTRICITY",
|
| 70 |
+
"58": "FR:FINANCIAL_SERVICES",
|
| 71 |
+
"59": "GB:GOLD",
|
| 72 |
+
"60": "GB:PLATINUM",
|
| 73 |
+
"61": "GB:SILVER",
|
| 74 |
+
"62": "GN:ALUMINIUM_ORE",
|
| 75 |
+
"63": "HK:DIAMONDS",
|
| 76 |
+
"64": "HK:ELECTRICAL_MACHINERY",
|
| 77 |
+
"65": "HK:SILVER",
|
| 78 |
+
"66": "ID:COAL",
|
| 79 |
+
"67": "ID:FERROALLOYS",
|
| 80 |
+
"68": "ID:PALM_OIL",
|
| 81 |
+
"69": "ID:TIN",
|
| 82 |
+
"70": "IN:DIAMONDS",
|
| 83 |
+
"71": "IN:IT_SERVICES",
|
| 84 |
+
"72": "IN:RICE",
|
| 85 |
+
"73": "KR:SHIPS",
|
| 86 |
+
"74": "KZ:URANIUM",
|
| 87 |
+
"75": "LU:FINANCIAL_SERVICES",
|
| 88 |
+
"76": "MX:LEAD_ORE",
|
| 89 |
+
"77": "MX:PRECIOUS_METALS_ORE",
|
| 90 |
+
"78": "MY:PALM_OIL",
|
| 91 |
+
"79": "NA:URANIUM",
|
| 92 |
+
"80": "NG:URANIUM",
|
| 93 |
+
"81": "NL:COCOA",
|
| 94 |
+
"82": "NO:FISH",
|
| 95 |
+
"83": "NO:NATGAS",
|
| 96 |
+
"84": "NO:NICKEL_METAL",
|
| 97 |
+
"85": "PK:RICE",
|
| 98 |
+
"86": "PE:COPPER_ORE",
|
| 99 |
+
"87": "PE:LEAD_ORE",
|
| 100 |
+
"88": "PE:PRECIOUS_METALS_ORE",
|
| 101 |
+
"89": "PE:TIN",
|
| 102 |
+
"90": "PE:ZINC_ORE",
|
| 103 |
+
"91": "PH:NICKEL_ORE",
|
| 104 |
+
"92": "QA:NATGAS",
|
| 105 |
+
"93": "RU:COAL",
|
| 106 |
+
"94": "RU:PETROLEUM_CRUDE",
|
| 107 |
+
"95": "RU:PRECIOUS_METALS_ORE",
|
| 108 |
+
"96": "RU:WHEAT",
|
| 109 |
+
"97": "SE:COPPER_UNREFINED",
|
| 110 |
+
"98": "SG:FINANCIAL_SERVICES",
|
| 111 |
+
"99": "TH:RICE",
|
| 112 |
+
"100": "UA:CORN",
|
| 113 |
+
"101": "US:CHEMICALS_MISC",
|
| 114 |
+
"102": "US:CHEMICALS_ORGANIC",
|
| 115 |
+
"103": "US:CORN",
|
| 116 |
+
"104": "US:DIAMONDS",
|
| 117 |
+
"105": "US:EDIBLE_FRUITS",
|
| 118 |
+
"106": "US:LEAD_ORE",
|
| 119 |
+
"107": "US:MEAT",
|
| 120 |
+
"108": "US:NATGAS",
|
| 121 |
+
"109": "US:OPTICAL_INSTRUMENTS",
|
| 122 |
+
"110": "US:PETROLEUM_CRUDE",
|
| 123 |
+
"111": "US:PETROLEUM_REFINED",
|
| 124 |
+
"112": "US:PHARMACEUTICALS",
|
| 125 |
+
"113": "US:PLASTICS",
|
| 126 |
+
"114": "US:PLATINUM",
|
| 127 |
+
"115": "US:RARE_GASES",
|
| 128 |
+
"116": "US:SOYBEAN",
|
| 129 |
+
"117": "US:TRAVEL",
|
| 130 |
+
"118": "US:WHEAT",
|
| 131 |
+
"119": "US:ZINC_ORE",
|
| 132 |
+
"120": "VN:FOOTWEAR",
|
| 133 |
+
"121": "VN:RICE",
|
| 134 |
+
"122": "ZA:FERROALLOYS",
|
| 135 |
+
"123": "ZA:PLATINUM",
|
| 136 |
+
"124": "ZM:COPPER_UNREFINED"
|
| 137 |
},
|
| 138 |
"initializer_range": 0.02,
|
| 139 |
"intermediate_size": 3072,
|
| 140 |
"label2id": {
|
| 141 |
+
"5": "AU:IRON_ORE",
|
| 142 |
+
"AE:DIAMONDS": 0,
|
| 143 |
+
"AE:PETROLEUM_CRUDE": 1,
|
| 144 |
+
"AR:CORN": 2,
|
| 145 |
+
"AU:ALUMINIUM_ORE": 3,
|
| 146 |
+
"AU:COAL": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
},
|
| 148 |
"layer_norm_eps": 1e-12,
|
| 149 |
"max_position_embeddings": 512,
|
checkpoint-35/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439415268
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146c25fa67437b50bbf2d45b899934fa9448b76639fd3dace3bbb85c4a3771de
|
| 3 |
size 439415268
|
checkpoint-35/special_tokens_map.json
CHANGED
|
@@ -1,7 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 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 |
}
|
checkpoint-35/tokenizer_config.json
CHANGED
|
@@ -46,12 +46,19 @@
|
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
|
|
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"never_split": null,
|
|
|
|
| 51 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
|
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
"never_split": null,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
"pad_token": "[PAD]",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
"sep_token": "[SEP]",
|
| 57 |
+
"stride": 0,
|
| 58 |
"strip_accents": null,
|
| 59 |
"tokenize_chinese_chars": true,
|
| 60 |
"tokenizer_class": "BertTokenizer",
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
"unk_token": "[UNK]"
|
| 64 |
}
|
checkpoint-35/trainer_state.json
CHANGED
|
@@ -10,23 +10,23 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.2857142857142857,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
"learning_rate": 2.9411764705882355e-06,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.5714285714285714,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
"learning_rate": 5.882352941176471e-06,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.8571428571428571,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
"learning_rate": 8.823529411764707e-06,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
|
@@ -35,18 +35,18 @@
|
|
| 35 |
"eval_f1": 0.0,
|
| 36 |
"eval_f1_macro": 0.0,
|
| 37 |
"eval_f1_micro": 0.0,
|
| 38 |
-
"eval_hamming_loss": 0.
|
| 39 |
-
"eval_hamming_score": 0.
|
| 40 |
-
"eval_loss": 0.
|
| 41 |
"eval_precision": 0.0,
|
| 42 |
"eval_precision_macro": 0.0,
|
| 43 |
"eval_precision_micro": 0.0,
|
| 44 |
"eval_recall": 0.0,
|
| 45 |
"eval_recall_macro": 0.0,
|
| 46 |
"eval_recall_micro": 0.0,
|
| 47 |
-
"eval_runtime": 0.
|
| 48 |
-
"eval_samples_per_second": 1.
|
| 49 |
-
"eval_steps_per_second": 1.
|
| 50 |
"eval_subset_accuracy": 0.0,
|
| 51 |
"step": 35
|
| 52 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.2857142857142857,
|
| 13 |
+
"grad_norm": 0.7777325510978699,
|
| 14 |
"learning_rate": 2.9411764705882355e-06,
|
| 15 |
+
"loss": 0.5875,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.5714285714285714,
|
| 20 |
+
"grad_norm": 0.754690945148468,
|
| 21 |
"learning_rate": 5.882352941176471e-06,
|
| 22 |
+
"loss": 0.5697,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.8571428571428571,
|
| 27 |
+
"grad_norm": 0.7596510648727417,
|
| 28 |
"learning_rate": 8.823529411764707e-06,
|
| 29 |
+
"loss": 0.5388,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
|
|
|
| 35 |
"eval_f1": 0.0,
|
| 36 |
"eval_f1_macro": 0.0,
|
| 37 |
"eval_f1_micro": 0.0,
|
| 38 |
+
"eval_hamming_loss": 0.072,
|
| 39 |
+
"eval_hamming_score": 0.928,
|
| 40 |
+
"eval_loss": 0.49661701917648315,
|
| 41 |
"eval_precision": 0.0,
|
| 42 |
"eval_precision_macro": 0.0,
|
| 43 |
"eval_precision_micro": 0.0,
|
| 44 |
"eval_recall": 0.0,
|
| 45 |
"eval_recall_macro": 0.0,
|
| 46 |
"eval_recall_micro": 0.0,
|
| 47 |
+
"eval_runtime": 0.6244,
|
| 48 |
+
"eval_samples_per_second": 1.602,
|
| 49 |
+
"eval_steps_per_second": 1.602,
|
| 50 |
"eval_subset_accuracy": 0.0,
|
| 51 |
"step": 35
|
| 52 |
}
|
config.json
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"architectures": [
|
|
|
|
|
|
|
| 4 |
"attention_probs_dropout_prob": 0.1,
|
| 5 |
"classifier_dropout": null,
|
| 6 |
"hidden_act": "gelu",
|
|
@@ -136,142 +138,15 @@
|
|
| 136 |
"initializer_range": 0.02,
|
| 137 |
"intermediate_size": 3072,
|
| 138 |
"label2id": {
|
|
|
|
| 139 |
"AE:DIAMONDS": 0,
|
| 140 |
"AE:PETROLEUM_CRUDE": 1,
|
| 141 |
"AR:CORN": 2,
|
| 142 |
"AU:ALUMINIUM_ORE": 3,
|
| 143 |
-
"AU:COAL": 4
|
| 144 |
-
"AU:IRON_ORE": 5,
|
| 145 |
-
"AU:NATGAS": 6,
|
| 146 |
-
"AU:WHEAT": 7,
|
| 147 |
-
"AU:ZINC_ORE": 8,
|
| 148 |
-
"BE:ZINC_METAL": 9,
|
| 149 |
-
"BO:ZINC_ORE": 10,
|
| 150 |
-
"BR:COFFEE": 11,
|
| 151 |
-
"BR:CORN": 12,
|
| 152 |
-
"BR:IRON_ORE": 13,
|
| 153 |
-
"BR:MEAT": 14,
|
| 154 |
-
"BR:SOYBEAN": 15,
|
| 155 |
-
"BR:SUGAR": 16,
|
| 156 |
-
"CA:ALUMINIUM_METAL": 17,
|
| 157 |
-
"CA:NICKEL_METAL": 18,
|
| 158 |
-
"CA:WHEAT": 19,
|
| 159 |
-
"CD:COPPER_REFINED": 20,
|
| 160 |
-
"CH:GOLD": 21,
|
| 161 |
-
"CH:PHARMACEUTICALS": 22,
|
| 162 |
-
"CL:COPPER_ORE": 23,
|
| 163 |
-
"CL:COPPER_REFINED": 24,
|
| 164 |
-
"CL:COPPER_UNREFINED": 25,
|
| 165 |
-
"CN:APPAREL": 26,
|
| 166 |
-
"CN:CARBON": 27,
|
| 167 |
-
"CN:CHEMICALS_MISC": 28,
|
| 168 |
-
"CN:CHEMICALS_ORGANIC": 29,
|
| 169 |
-
"CN:ELECTRICAL_MACHINERY": 30,
|
| 170 |
-
"CN:FURNITURE": 31,
|
| 171 |
-
"CN:MACHINERY": 32,
|
| 172 |
-
"CN:NICKEL_METAL": 33,
|
| 173 |
-
"CN:OPTICAL_INSTRUMENTS": 34,
|
| 174 |
-
"CN:PAPER": 35,
|
| 175 |
-
"CN:PLASTICS": 36,
|
| 176 |
-
"CN:RARE_GASES": 37,
|
| 177 |
-
"CN:RUBBER": 38,
|
| 178 |
-
"CN:SHIPS": 39,
|
| 179 |
-
"CN:SILVER": 40,
|
| 180 |
-
"CN:TOYS": 41,
|
| 181 |
-
"CN:VEHICLES": 42,
|
| 182 |
-
"CN:WOOD": 43,
|
| 183 |
-
"DE:AIRCRAFT": 44,
|
| 184 |
-
"DE:CHEMICALS_MISC": 45,
|
| 185 |
-
"DE:COCOA": 46,
|
| 186 |
-
"DE:FINANCIAL_SERVICES": 47,
|
| 187 |
-
"DE:OPTICAL_INSTRUMENTS": 48,
|
| 188 |
-
"DE:PAPER": 49,
|
| 189 |
-
"DE:PHARMACEUTICALS": 50,
|
| 190 |
-
"DE:RARE_GASES": 51,
|
| 191 |
-
"DE:VEHICLES": 52,
|
| 192 |
-
"FI:NICKEL_ORE": 53,
|
| 193 |
-
"FR:AIRCRAFT": 54,
|
| 194 |
-
"FR:BEVERAGES": 55,
|
| 195 |
-
"FR:COSMETICS": 56,
|
| 196 |
-
"FR:ELECTRICITY": 57,
|
| 197 |
-
"FR:FINANCIAL_SERVICES": 58,
|
| 198 |
-
"GB:GOLD": 59,
|
| 199 |
-
"GB:PLATINUM": 60,
|
| 200 |
-
"GB:SILVER": 61,
|
| 201 |
-
"GN:ALUMINIUM_ORE": 62,
|
| 202 |
-
"HK:DIAMONDS": 63,
|
| 203 |
-
"HK:ELECTRICAL_MACHINERY": 64,
|
| 204 |
-
"HK:SILVER": 65,
|
| 205 |
-
"ID:COAL": 66,
|
| 206 |
-
"ID:FERROALLOYS": 67,
|
| 207 |
-
"ID:PALM_OIL": 68,
|
| 208 |
-
"ID:TIN": 69,
|
| 209 |
-
"IN:DIAMONDS": 70,
|
| 210 |
-
"IN:IT_SERVICES": 71,
|
| 211 |
-
"IN:RICE": 72,
|
| 212 |
-
"KR:SHIPS": 73,
|
| 213 |
-
"KZ:URANIUM": 74,
|
| 214 |
-
"LU:FINANCIAL_SERVICES": 75,
|
| 215 |
-
"MX:LEAD_ORE": 76,
|
| 216 |
-
"MX:PRECIOUS_METALS_ORE": 77,
|
| 217 |
-
"MY:PALM_OIL": 78,
|
| 218 |
-
"NA:URANIUM": 79,
|
| 219 |
-
"NG:URANIUM": 80,
|
| 220 |
-
"NL:COCOA": 81,
|
| 221 |
-
"NO:FISH": 82,
|
| 222 |
-
"NO:NATGAS": 83,
|
| 223 |
-
"NO:NICKEL_METAL": 84,
|
| 224 |
-
"PK:RICE": 85,
|
| 225 |
-
"PE:COPPER_ORE": 86,
|
| 226 |
-
"PE:LEAD_ORE": 87,
|
| 227 |
-
"PE:PRECIOUS_METALS_ORE": 88,
|
| 228 |
-
"PE:TIN": 89,
|
| 229 |
-
"PE:ZINC_ORE": 90,
|
| 230 |
-
"PH:NICKEL_ORE": 91,
|
| 231 |
-
"QA:NATGAS": 92,
|
| 232 |
-
"RU:COAL": 93,
|
| 233 |
-
"RU:PETROLEUM_CRUDE": 94,
|
| 234 |
-
"RU:PRECIOUS_METALS_ORE": 95,
|
| 235 |
-
"RU:WHEAT": 96,
|
| 236 |
-
"SE:COPPER_UNREFINED": 97,
|
| 237 |
-
"SG:FINANCIAL_SERVICES": 98,
|
| 238 |
-
"TH:RICE": 99,
|
| 239 |
-
"UA:CORN": 100,
|
| 240 |
-
"US:CHEMICALS_MISC": 101,
|
| 241 |
-
"US:CHEMICALS_ORGANIC": 102,
|
| 242 |
-
"US:CORN": 103,
|
| 243 |
-
"US:DIAMONDS": 104,
|
| 244 |
-
"US:EDIBLE_FRUITS": 105,
|
| 245 |
-
"US:LEAD_ORE": 106,
|
| 246 |
-
"US:MEAT": 107,
|
| 247 |
-
"US:NATGAS": 108,
|
| 248 |
-
"US:OPTICAL_INSTRUMENTS": 109,
|
| 249 |
-
"US:PETROLEUM_CRUDE": 110,
|
| 250 |
-
"US:PETROLEUM_REFINED": 111,
|
| 251 |
-
"US:PHARMACEUTICALS": 112,
|
| 252 |
-
"US:PLASTICS": 113,
|
| 253 |
-
"US:PLATINUM": 114,
|
| 254 |
-
"US:RARE_GASES": 115,
|
| 255 |
-
"US:SOYBEAN": 116,
|
| 256 |
-
"US:TRAVEL": 117,
|
| 257 |
-
"US:WHEAT": 118,
|
| 258 |
-
"US:ZINC_ORE": 119,
|
| 259 |
-
"VN:FOOTWEAR": 120,
|
| 260 |
-
"VN:RICE": 121,
|
| 261 |
-
"ZA:FERROALLOYS": 122,
|
| 262 |
-
"ZA:PLATINUM": 123,
|
| 263 |
-
"ZM:COPPER_UNREFINED": 124
|
| 264 |
-
},
|
| 265 |
-
"initializer_range": 0.02,
|
| 266 |
-
"intermediate_size": 3072,
|
| 267 |
-
"label2id": {
|
| 268 |
-
"AE:DIAMONDS": 0,
|
| 269 |
-
"AE:PETROLEUM_CRUDE": 1,
|
| 270 |
-
"AR:CORN": 2,
|
| 271 |
-
"AU:ALUMINIUM_ORE": 3,
|
| 272 |
-
"AU:COAL": 4,
|
| 273 |
-
"5": "AU:IRON_ORE"
|
| 274 |
},
|
|
|
|
|
|
|
| 275 |
"model_type": "bert",
|
| 276 |
"num_attention_heads": 12,
|
| 277 |
"num_hidden_layers": 12,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Bencode92/tradepulse-finbert-correlations",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"hidden_act": "gelu",
|
|
|
|
| 138 |
"initializer_range": 0.02,
|
| 139 |
"intermediate_size": 3072,
|
| 140 |
"label2id": {
|
| 141 |
+
"5": "AU:IRON_ORE",
|
| 142 |
"AE:DIAMONDS": 0,
|
| 143 |
"AE:PETROLEUM_CRUDE": 1,
|
| 144 |
"AR:CORN": 2,
|
| 145 |
"AU:ALUMINIUM_ORE": 3,
|
| 146 |
+
"AU:COAL": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
},
|
| 148 |
+
"layer_norm_eps": 1e-12,
|
| 149 |
+
"max_position_embeddings": 512,
|
| 150 |
"model_type": "bert",
|
| 151 |
"num_attention_heads": 12,
|
| 152 |
"num_hidden_layers": 12,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439415268
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146c25fa67437b50bbf2d45b899934fa9448b76639fd3dace3bbb85c4a3771de
|
| 3 |
size 439415268
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 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_config.json
CHANGED
|
@@ -46,12 +46,19 @@
|
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
|
|
|
| 49 |
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
"never_split": null,
|
|
|
|
| 51 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
|
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
"never_split": null,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
"pad_token": "[PAD]",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
"sep_token": "[SEP]",
|
| 57 |
+
"stride": 0,
|
| 58 |
"strip_accents": null,
|
| 59 |
"tokenize_chinese_chars": true,
|
| 60 |
"tokenizer_class": "BertTokenizer",
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
"unk_token": "[UNK]"
|
| 64 |
}
|