Training in progress, step 500

added_tokens.json

@@ -1,7 +1,8 @@
 {
-  "[CLS]": 101,
-  "[MASK]": 103,
-  "[PAD]": 0,
-  "[SEP]": 102,
-  "[UNK]": 100
+  "[CLS]": 2,
+  "[FRN]": 5,
+  "[MASK]": 4,
+  "[PAD]": 1,
+  "[SEP]": 3,
+  "[UNK]": 0
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "Tural/language-modeling-from-scratch-ml",
   "architectures": [
     "BertForSequenceClassification"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55be836b8c3805eda54affc7bc3d51a18169b0d0f75c57d6c2615fe9af67d084
-size 438006577
+oid sha256:182b99770bc77bf0c4b8adfc17cd66678c4b19214ca5449fbac3c0ef8d597f45
+size 438007022

special_tokens_map.json

@@ -1,4 +1,12 @@
 {
+  "additional_special_tokens": [
+    "[UNK]",
+    "[PAD]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]",
+    "[FRN]"
+  ],
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,21 +32,36 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "5": {
+      "content": "[FRN]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "[UNK]",
+    "[PAD]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]",
+    "[FRN]"
+  ],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760016632cb210f9a310352867c0b6186e6d6c39e0c20094f2eb11d0469e0643
-size 4091
+oid sha256:67c005e8e5159b881ed8be646200a06f1edb75d4bf9945432c5fa59b921a6156
+size 4600