Training in progress, step 200

config.json

@@ -40,7 +40,7 @@
     "tie_word_embeddings": true,
     "type_vocab_size": 2,
     "use_cache": true,
-    "vocab_size": 52
+    "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": 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 sha256:205d4085ca2ae26177a33b58f8a5c43c74f44ae6844a28e4a05ee5414ad08b6e
-size 31205552
+oid sha256:c19909c515fc1735fc2b10f588272c28ab3af9a8b5e8302e31c78102024a7f86
+size 31207604

tokenizer.json

@@ -113,41 +113,43 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "99": 16,
-      "10": 17,
-      "11": 18,
-      "12": 19,
-      "97": 20,
-      "98": 21,
-      "13": 22,
-      "96": 23,
-      "14": 24,
-      "95": 25,
-      "94": 26,
+      "=": 16,
+      "99": 17,
+      "10": 18,
+      "98": 19,
+      "11": 20,
+      "97": 21,
+      "12": 22,
+      "13": 23,
+      "96": 24,
+      "14": 25,
+      "95": 26,
       "15": 27,
-      "16": 28,
+      "94": 28,
       "93": 29,
-      "17": 30,
+      "16": 30,
       "92": 31,
-      "91": 32,
-      "18": 33,
-      "19": 34,
+      "17": 32,
+      "91": 33,
+      "18": 34,
       "90": 35,
-      "20": 36,
-      "89": 37,
-      "21": 38,
-      "88": 39,
-      "22": 40,
-      "87": 41,
-      "23": 42,
-      "24": 43,
-      "85": 44,
-      "86": 45,
-      "25": 46,
-      "84": 47,
-      "26": 48,
-      "82": 49,
-      "83": 50
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
+      "22": 41,
+      "87": 42,
+      "23": 43,
+      "86": 44,
+      "85": 45,
+      "24": 46,
+      "25": 47,
+      "84": 48,
+      "83": 49,
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
       [
@@ -159,20 +161,20 @@
         "0"
       ],
       [
-        "1",
-        "1"
+        "9",
+        "8"
       ],
       [
         "1",
-        "2"
+        "1"
       ],
       [
         "9",
         "7"
       ],
       [
-        "9",
-        "8"
+        "1",
+        "2"
       ],
       [
         "1",
@@ -190,17 +192,13 @@
         "9",
         "5"
       ],
-      [
-        "9",
-        "4"
-      ],
       [
         "1",
         "5"
       ],
       [
-        "1",
-        "6"
+        "9",
+        "4"
       ],
       [
         "9",
@@ -208,12 +206,16 @@
       ],
       [
         "1",
-        "7"
+        "6"
       ],
       [
         "9",
         "2"
       ],
+      [
+        "1",
+        "7"
+      ],
       [
         "9",
         "1"
@@ -222,14 +224,14 @@
         "1",
         "8"
       ],
-      [
-        "1",
-        "9"
-      ],
       [
         "9",
         "0"
       ],
+      [
+        "1",
+        "9"
+      ],
       [
         "2",
         "0"
@@ -259,16 +261,16 @@
         "3"
       ],
       [
-        "2",
-        "4"
+        "8",
+        "6"
       ],
       [
         "8",
         "5"
       ],
       [
-        "8",
-        "6"
+        "2",
+        "4"
       ],
       [
         "2",
@@ -278,17 +280,21 @@
         "8",
         "4"
       ],
+      [
+        "8",
+        "3"
+      ],
       [
         "2",
         "6"
       ],
       [
-        "8",
-        "2"
+        "2",
+        "7"
       ],
       [
         "8",
-        "3"
+        "2"
       ]
     ]
   }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b4a81af612cc362804a1fc1b3c91f73019a8bdc750d176166db91cba1ab113
+oid sha256:6012fd436d7b395a674f8fad5b4e9927048710fbf3da4b6ecb6eab2d0265e7da
 size 5329