Train with Main verb Sub verb tags

added_tokens.json

@@ -121,6 +121,7 @@
   "[GERUND_SUFFIX:CLASS_2:ORAL_VOWEL_ENDING]": 32170,
   "[IMPERATIVE_PREFIX:2pp]": 32144,
   "[IMPERATIVE_PREFIX:2ps]": 32153,
+  "[MAIN_VERB]": 32196,
   "[NEGATION_PARTICLE:NA]": 32152,
   "[NEGATION_PARTICLE:UME]": 32135,
   "[NEGATION_PREFIX]": 32143,
@@ -164,6 +165,7 @@
   "[SUBJECT_PREFIX:2pp]": 32119,
   "[SUBJECT_PREFIX:2ps]": 32130,
   "[SUBJECT_PREFIX:3p]": 32171,
+  "[SUB_VERB]": 32197,
   "a'e": 32127,
   "amo": 32104,
   "bo": 32110,

config.json

@@ -57,5 +57,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_cache": true,
-  "vocab_size": 32196
+  "vocab_size": 32198
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6429f08c9d32f73aca7ddb79ef42875ea88b53e600934f4c5dffe4b8ae5ac131
-size 242181160
+oid sha256:0c8b330e8b3e8fbff4a45942c27fe14746e74b2cdbc5b4027ddca51fcbbf9c2b
+size 242185256

special_tokens_map.json

@@ -119,6 +119,13 @@
       "rstrip": false,
       "single_word": false
     },
+    {
+      "content": "[MAIN_VERB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
     {
       "content": "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]",
       "lstrip": false,
@@ -168,6 +175,13 @@
       "rstrip": false,
       "single_word": false
     },
+    {
+      "content": "[SUB_VERB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
     {
       "content": "[GERUND_SUFFIX:CLASS_1:IYU]",
       "lstrip": false,
@@ -190,14 +204,14 @@
       "single_word": false
     },
     {
-      "content": "[NEGATION_SUFFIX]",
+      "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
+      "content": "[NEGATION_SUFFIX]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -246,7 +260,7 @@
       "single_word": false
     },
     {
-      "content": "[SUBJECT:1ps]",
+      "content": "[SUBJECT:1ppe]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -260,7 +274,7 @@
       "single_word": false
     },
     {
-      "content": "[SUBJECT:1ppe]",
+      "content": "[SUBJECT:1ps]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -358,14 +372,14 @@
       "single_word": false
     },
     {
-      "content": "opo",
+      "content": "[OBJECT_MARKER:3p:DEFAULT]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "[OBJECT_MARKER:3p:DEFAULT]",
+      "content": "opo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -428,14 +442,14 @@
       "single_word": false
     },
     {
-      "content": "endé",
+      "content": "namo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "namo",
+      "content": "endé",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -526,7 +540,7 @@
       "single_word": false
     },
     {
-      "content": "ixé",
+      "content": "[SUBJECT_PREFIX:1ps]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -540,21 +554,21 @@
       "single_word": false
     },
     {
-      "content": "[SUBJECT_PREFIX:1ps]",
+      "content": "ixé",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "ramo",
+      "content": "pa",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "pa",
+      "content": "ramo",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -659,14 +673,14 @@
       "single_word": false
     },
     {
-      "content": "[SUBJECT:2ps]",
+      "content": "[PLURIFORM_PREFIX:R]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "[PLURIFORM_PREFIX:R]",
+      "content": "[SUBJECT:2ps]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer_config.json

@@ -1680,6 +1680,22 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32196": {
+      "content": "[MAIN_VERB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32197": {
+      "content": "[SUB_VERB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -1700,6 +1716,7 @@
     "[NEGATION_PARTICLE:NA]",
     "[IMPERATIVE_PREFIX:2ps]",
     "îos",
+    "[MAIN_VERB]",
     "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]",
     "[PLURIFORM_PREFIX:S]",
     "û",
@@ -1707,20 +1724,21 @@
     "[OBJECT:1ppi]",
     "abo",
     "[GERUND_SUFFIX:CLASS_1]",
+    "[SUB_VERB]",
     "[GERUND_SUFFIX:CLASS_1:IYU]",
     "îo",
     "i",
-    "[NEGATION_SUFFIX]",
     "[GERUND_SUBJECT_PREFIX:1ppe]",
+    "[NEGATION_SUFFIX]",
     "[SUBJECT:3p]",
     "[IMPERATIVE_PREFIX:2pp]",
     "́",
     "xe",
     "a'e",
     "t",
-    "[SUBJECT:1ps]",
-    "a",
     "[SUBJECT:1ppe]",
+    "a",
+    "[SUBJECT:1ps]",
     "[SUBJECT_PREFIX:1ppe]",
     "amo",
     "[OBJECT:2ps]",
@@ -1734,8 +1752,8 @@
     "[PERMISSIVE_PREFIX:VOWEL]",
     "pe",
     "nde",
-    "opo",
     "[OBJECT_MARKER:3p:DEFAULT]",
+    "opo",
     "[GERUND_SUBJECT_PREFIX:2ps]",
     "[OBJECT:3p]",
     "îandé",
@@ -1744,8 +1762,8 @@
     "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
     "[OBJECT_MARKER:3p:MONOSYLLABIC]",
     "peîepé",
-    "endé",
     "namo",
+    "endé",
     "[GERUND_SUFFIX:CLASS_1:R]",
     "[SUBJECT:2pp:OBJECT_1P]",
     "mo",
@@ -1758,11 +1776,11 @@
     "[SUBJECT_PREFIX:3p]",
     "r",
     "[NEGATION_SUFFIX:VOWEL_ENDING]",
-    "ixé",
-    "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
     "[SUBJECT_PREFIX:1ps]",
-    "ramo",
+    "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
+    "ixé",
     "pa",
+    "ramo",
     "ere",
     "[OBJECT:REFLEXIVE]",
     "[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
@@ -1777,8 +1795,8 @@
     "[PERMISSIVE_PREFIX:CONSONANT]",
     "oré",
     "umẽ",
-    "[SUBJECT:2ps]",
     "[PLURIFORM_PREFIX:R]",
+    "[SUBJECT:2ps]",
     "o",
     "[SUBJECT:2ps:OBJECT_1P]",
     "îa",