Training in progress, epoch 0

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "<s_donut_rus>": 62518
+  "<s_500k>": 35054
 }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef009ae2ede7beded780cfa82e11d2d977473cb6ddf9c3b5bdce3c367497fc01
+size 943862

special_tokens_map.json

@@ -1,5 +1,15 @@
 {
+  "bos_token": "<s>",
+  "cls_token": "<s>",
   "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<pad>",
+  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,13 +1,21 @@
 {
+  "bos_token": "<s>",
+  "cls_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 512,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
-  "separate_vocabs": false,
-  "source_lang": "ru",
+  "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "target_lang": "en",
-  "tokenizer_class": "MarianTokenizer",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/6ea33bfad55f516eeb1e52bb6e3f5c198c976c6ebfaa7e1fb9f56b33b2ddc8a9.f6ac38e94db1fb749ad0f52af2f7cd5b7863b9b30f1aa680a1b0d22ec09b717d",
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }