Training in progress, step 81500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc73315c011c667fae5118de18857e215a6c140faeee78bbe45de306c97057e5
-size 501023389
+oid sha256:5bffa40dd6e42b28764d59bfc7500d4a9ed9ea35d01e701ed52eadec35b03d92
+size 2240706037

special_tokens_map.json

@@ -1,30 +1,15 @@
 {
-  "bos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,40 +1,19 @@
 {
-  "add_bos_token": true,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": {
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
     "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
+    "content": "<mask>",
+    "lstrip": true,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53313092d109a391e0898b0bee6844ea392965c8c5bf148cfbb0c514976d9e88
+oid sha256:5008108e53cdb8e7f240c97ba92b03b41d129ae0ed84af3900966084794ad7c8
 size 4027