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 sha256:19986798d177026e1af84d3161899f23cfd3719af1f3c93af4c02657649d999f
-size 31205552
+oid sha256:ee6e319ab7f16ceec9768a1e3f9c211d04f661fed06737d591d937280a704670
+size 31207604

tokenizer.json

@@ -113,42 +113,43 @@
       "7": 13,
       "8": 14,
       "9": 15,
-      "10": 16,
-      "99": 17,
+      "=": 16,
+      "10": 17,
       "11": 18,
-      "98": 19,
-      "12": 20,
-      "13": 21,
-      "96": 22,
-      "97": 23,
-      "95": 24,
-      "14": 25,
-      "94": 26,
-      "15": 27,
-      "16": 28,
-      "93": 29,
-      "17": 30,
-      "92": 31,
+      "12": 19,
+      "13": 20,
+      "14": 21,
+      "15": 22,
+      "99": 23,
+      "98": 24,
+      "16": 25,
+      "97": 26,
+      "96": 27,
+      "17": 28,
+      "95": 29,
+      "94": 30,
+      "93": 31,
       "18": 32,
-      "91": 33,
-      "19": 34,
+      "92": 33,
+      "91": 34,
       "90": 35,
-      "20": 36,
-      "89": 37,
-      "21": 38,
-      "88": 39,
-      "87": 40,
+      "19": 36,
+      "20": 37,
+      "89": 38,
+      "21": 39,
+      "88": 40,
       "22": 41,
-      "86": 42,
+      "87": 42,
       "23": 43,
-      "24": 44,
-      "85": 45,
-      "25": 46,
-      "84": 47,
-      "26": 48,
+      "86": 44,
+      "24": 45,
+      "85": 46,
+      "25": 47,
+      "84": 48,
       "83": 49,
-      "27": 50,
-      "82": 51
+      "26": 50,
+      "27": 51,
+      "82": 52
     },
     "merges": [
       [
@@ -156,27 +157,35 @@
         "0"
       ],
       [
-        "9",
-        "9"
+        "1",
+        "1"
       ],
       [
         "1",
-        "1"
+        "2"
       ],
       [
-        "9",
-        "8"
+        "1",
+        "3"
       ],
       [
         "1",
-        "2"
+        "4"
       ],
       [
         "1",
-        "3"
+        "5"
+      ],
+      [
+        "9",
+        "9"
       ],
       [
         "9",
+        "8"
+      ],
+      [
+        "1",
         "6"
       ],
       [
@@ -185,23 +194,19 @@
       ],
       [
         "9",
-        "5"
+        "6"
       ],
       [
         "1",
-        "4"
+        "7"
       ],
       [
         "9",
-        "4"
-      ],
-      [
-        "1",
         "5"
       ],
       [
-        "1",
-        "6"
+        "9",
+        "4"
       ],
       [
         "9",
@@ -209,28 +214,24 @@
       ],
       [
         "1",
-        "7"
+        "8"
       ],
       [
         "9",
         "2"
       ],
       [
-        "1",
-        "8"
+        "9",
+        "1"
       ],
       [
         "9",
-        "1"
+        "0"
       ],
       [
         "1",
         "9"
       ],
-      [
-        "9",
-        "0"
-      ],
       [
         "2",
         "0"
@@ -247,22 +248,22 @@
         "8",
         "8"
       ],
-      [
-        "8",
-        "7"
-      ],
       [
         "2",
         "2"
       ],
       [
         "8",
-        "6"
+        "7"
       ],
       [
         "2",
         "3"
       ],
+      [
+        "8",
+        "6"
+      ],
       [
         "2",
         "4"
@@ -279,14 +280,14 @@
         "8",
         "4"
       ],
-      [
-        "2",
-        "6"
-      ],
       [
         "8",
         "3"
       ],
+      [
+        "2",
+        "6"
+      ],
       [
         "2",
         "7"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4145346caae726bcb96257bccf166a2582ba0ecf695103b3ed453d2fc2669c
+oid sha256:5a9aaf3ec80136ea55ae8c9a04d0edde6aa2b3cbcf6781427d7419c126a376e8
 size 5329