Training in progress, epoch 1

config.json

@@ -33,7 +33,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.3",
+  "transformers_version": "4.34.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 25005

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04b28ca5dfddf555fb61837ed6fc23d371319f7c79cc4201c50f17a2fbee731
-size 421055857
+oid sha256:1b1294e345916ee21c7cc4adfaabf0096bef8bcf5b40d1325acf6549529fd9ec
+size 421056302

special_tokens_map.json

@@ -10,7 +10,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -84,7 +84,7 @@
       "single_word": false,
       "lstrip": true,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],
@@ -100219,6 +100219,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,4 +1,70 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<_>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "additional_special_tokens": [
     "<s>NOTUSED",
     "</s>NOTUSED",
@@ -8,14 +74,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31040e7ab8aaa4c07478a66f547b727d76468945f54f9414ecf20059f36d8202
-size 4027
+oid sha256:7b90ab1639d1a028065b523bf7432f452233545600578274e3cc3c5e18691004
+size 4536