Training in progress, step 240

config.json

@@ -78,7 +78,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 53
   },
   "decoder_start_token_id": 2,
   "encoder": {
@@ -157,7 +157,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 52
+    "vocab_size": 53
   },
   "eos_token_id": 0,
   "is_encoder_decoder": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79967d5cfdbf3b3fe96fd90e7336e057644b4a9eadcd0379c5e779d648c19929
-size 31205552
+oid sha256:203a9f414a0392839b2cab6be99a4a5e632f765051af0c7aa67dd076cb0f8d78
+size 31207604

tokenizer.json

@@ -113,72 +113,57 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
-      "99": 17,
+      "=": 16,
+      "10": 17,
       "11": 18,
-      "98": 19,
-      "12": 20,
-      "97": 21,
-      "96": 22,
-      "13": 23,
-      "14": 24,
-      "95": 25,
-      "94": 26,
-      "15": 27,
-      "93": 28,
-      "16": 29,
-      "17": 30,
-      "92": 31,
-      "91": 32,
-      "18": 33,
-      "19": 34,
+      "12": 19,
+      "13": 20,
+      "14": 21,
+      "15": 22,
+      "99": 23,
+      "16": 24,
+      "98": 25,
+      "97": 26,
+      "96": 27,
+      "17": 28,
+      "95": 29,
+      "94": 30,
+      "18": 31,
+      "93": 32,
+      "92": 33,
+      "91": 34,
       "90": 35,
-      "89": 36,
+      "19": 36,
       "20": 37,
-      "21": 38,
+      "89": 38,
       "88": 39,
-      "22": 40,
-      "23": 41,
+      "21": 40,
+      "22": 41,
       "87": 42,
-      "86": 43,
-      "24": 44,
-      "85": 45,
-      "25": 46,
-      "84": 47,
-      "26": 48,
-      "83": 49,
-      "27": 50,
-      "82": 51
+      "23": 43,
+      "86": 44,
+      "24": 45,
+      "85": 46,
+      "25": 47,
+      "84": 48,
+      "26": 49,
+      "83": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
       [
         "1",
         "0"
       ],
-      [
-        "9",
-        "9"
-      ],
       [
         "1",
         "1"
       ],
-      [
-        "9",
-        "8"
-      ],
       [
         "1",
         "2"
       ],
-      [
-        "9",
-        "7"
-      ],
-      [
-        "9",
-        "6"
-      ],
       [
         "1",
         "3"
@@ -188,23 +173,27 @@
         "4"
       ],
       [
-        "9",
+        "1",
         "5"
       ],
       [
         "9",
-        "4"
+        "9"
       ],
       [
         "1",
-        "5"
+        "6"
       ],
       [
         "9",
-        "3"
+        "8"
       ],
       [
-        "1",
+        "9",
+        "7"
+      ],
+      [
+        "9",
         "6"
       ],
       [
@@ -213,26 +202,34 @@
       ],
       [
         "9",
-        "2"
+        "5"
       ],
       [
         "9",
-        "1"
+        "4"
       ],
       [
         "1",
         "8"
       ],
       [
-        "1",
-        "9"
+        "9",
+        "3"
+      ],
+      [
+        "9",
+        "2"
+      ],
+      [
+        "9",
+        "1"
       ],
       [
         "9",
         "0"
       ],
       [
-        "8",
+        "1",
         "9"
       ],
       [
@@ -240,8 +237,8 @@
         "0"
       ],
       [
-        "2",
-        "1"
+        "8",
+        "9"
       ],
       [
         "8",
@@ -249,16 +246,20 @@
       ],
       [
         "2",
-        "2"
+        "1"
       ],
       [
         "2",
-        "3"
+        "2"
       ],
       [
         "8",
         "7"
       ],
+      [
+        "2",
+        "3"
+      ],
       [
         "8",
         "6"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec00b9bec78debd9cb4b622b44c318365ee067e8a4ac53b65b26e63f79e39d2b
+oid sha256:a6d5de93eea72009098ce9a3f452b5fa74a32ef73f48db80a9d72886d7a4bf29
 size 5368