Training done

added_tokens.json

@@ -2,10 +2,10 @@
   "</s_Active ingredient>": 57526,
   "</s_Uses>": 57528,
   "</s_Warnings>": 57530,
-  "<drug_label>": 57531,
   "<s_Active ingredient>": 57525,
   "<s_Uses>": 57527,
   "<s_Warnings>": 57529,
+  "<s_cord-v2>": 57531,
   "<s_iitcdip>": 57523,
   "<s_synthdog>": 57524,
   "<sep/>": 57522

preprocessor_config.json

@@ -19,8 +19,8 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 1280,
-    "width": 960
-  }
+  "size": [
+    960,
+    1280
+  ]
 }

tokenizer_config.json

@@ -113,7 +113,7 @@
       "special": false
     },
     "57531": {
-      "content": "<drug_label>",
+      "content": "<s_cord-v2>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -130,18 +130,11 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 768,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }