Training in progress, step 360

config.json

@@ -40,7 +40,7 @@
     "tie_word_embeddings": true,
     "type_vocab_size": 2,
     "use_cache": true,
-    "vocab_size": 51
+    "vocab_size": 53
   },
   "decoder_start_token_id": 2,
   "dtype": "float32",
@@ -82,7 +82,7 @@
     "tie_word_embeddings": true,
     "type_vocab_size": 2,
     "use_cache": true,
-    "vocab_size": 51
+    "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 sha256:09df36d04c46186083703a6aac94d13ba57510596a4f5635b0ec3cb946eb98b8
-size 31203500
+oid sha256:b61de5bd46ee34899d08a1fe9ca7bd4b13b48fa6b9475e8751194698c1b33585
+size 31207604

tokenizer.json

@@ -113,51 +113,53 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "99": 16,
+      "=": 16,
       "10": 17,
-      "98": 18,
-      "11": 19,
-      "97": 20,
-      "12": 21,
-      "96": 22,
-      "13": 23,
-      "14": 24,
+      "99": 18,
+      "98": 19,
+      "11": 20,
+      "97": 21,
+      "12": 22,
+      "96": 23,
+      "13": 24,
       "95": 25,
-      "94": 26,
-      "15": 27,
-      "93": 28,
-      "16": 29,
-      "17": 30,
-      "92": 31,
-      "91": 32,
+      "14": 26,
+      "94": 27,
+      "15": 28,
+      "93": 29,
+      "16": 30,
+      "17": 31,
+      "92": 32,
       "18": 33,
-      "19": 34,
+      "91": 34,
       "90": 35,
-      "89": 36,
+      "19": 36,
       "20": 37,
-      "21": 38,
-      "88": 39,
-      "87": 40,
-      "22": 41,
-      "86": 42,
+      "89": 38,
+      "21": 39,
+      "88": 40,
+      "87": 41,
+      "22": 42,
       "23": 43,
-      "85": 44,
-      "24": 45,
-      "84": 46,
+      "86": 44,
+      "85": 45,
+      "24": 46,
       "25": 47,
-      "26": 48,
+      "84": 48,
       "83": 49,
-      "27": 50
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
-      [
-        "9",
-        "9"
-      ],
       [
         "1",
         "0"
       ],
+      [
+        "9",
+        "9"
+      ],
       [
         "9",
         "8"
@@ -182,14 +184,14 @@
         "1",
         "3"
       ],
-      [
-        "1",
-        "4"
-      ],
       [
         "9",
         "5"
       ],
+      [
+        "1",
+        "4"
+      ],
       [
         "9",
         "4"
@@ -214,30 +216,30 @@
         "9",
         "2"
       ],
-      [
-        "9",
-        "1"
-      ],
       [
         "1",
         "8"
       ],
       [
-        "1",
-        "9"
+        "9",
+        "1"
       ],
       [
         "9",
         "0"
       ],
       [
-        "8",
+        "1",
         "9"
       ],
       [
         "2",
         "0"
       ],
+      [
+        "8",
+        "9"
+      ],
       [
         "2",
         "1"
@@ -254,24 +256,20 @@
         "2",
         "2"
       ],
-      [
-        "8",
-        "6"
-      ],
       [
         "2",
         "3"
       ],
       [
         "8",
-        "5"
+        "6"
       ],
       [
-        "2",
-        "4"
+        "8",
+        "5"
       ],
       [
-        "8",
+        "2",
         "4"
       ],
       [
@@ -279,16 +277,24 @@
         "5"
       ],
       [
-        "2",
-        "6"
+        "8",
+        "4"
       ],
       [
         "8",
         "3"
       ],
+      [
+        "2",
+        "6"
+      ],
       [
         "2",
         "7"
+      ],
+      [
+        "8",
+        "2"
       ]
     ]
   }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89ef723dac59e368374c6a402ae1cc91425f0535cc64f74566f34752e0d1bde
+oid sha256:5c7302403c5be8babf39d19ad5e90e30dbee4ec7e55d81788f26a6ff7c4403c7
 size 5329