Trained with abstracts.

README.md

@@ -1,28 +0,0 @@
----
-license: apache-2.0
----
-| Label Name                        | Label ID |
-|-----------------------------------|----------|
-| Temperature Indicators            | 0        |
-| Cryospheric Climate Indicators    | 1        |
-| Severe Storms                     | 2        |
-| Heat                              | 3        |
-| Wildfires                         | 4        |
-| Water Quality                     | 5        |
-| Greenhouse Gases                  | 6        |
-| Volcanic Eruptions                | 7        |
-| Earthquakes                       | 8        |
-| Land Use and Cover Change         | 9        |
-| Sun-Earth Interactions            | 10       |
-| Agriculture                       | 11       |
-| Extreme Weather                   | 12       |
-| Public Health                     | 13       |
-| Ecosystems                        | 14       |
-| Floods                            | 15       |
-| Ecosystem Species                 | 16       |
-| Energy Production/Use             | 17       |
-| Landslides                        | 18       |
-| Air Quality                       | 19       |
-| Teleconnections                   | 20       |
-| Validation                        | 21       |
-| Droughts                          | 22       |

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -69,7 +69,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.27.3",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 31116

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a56ac18d87035dace3d2d68f2af0e32bf34a24e25cc67f07e4891f245dc7a69
-size 439897269
+oid sha256:511de2a141be1652f7cc36743c0daa50705c8d64308429987937e54a956f7126
+size 439892849

tokenizer.json

@@ -19,48 +19,48 @@
   "added_tokens": [
     {
       "id": 0,
-      "special": true,
       "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 100,
-      "special": true,
       "content": "[UNK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 101,
-      "special": true,
       "content": "[CLS]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 102,
-      "special": true,
       "content": "[SEP]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     },
     {
       "id": 103,
-      "special": true,
       "content": "[MASK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,4 +1,48 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
@@ -7,7 +51,6 @@
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",