Training done

preprocessor_config.json

@@ -2,15 +2,14 @@
   "do_align_long_axis": false,
   "do_normalize": true,
   "do_pad": true,
-  "do_rescale": true,
   "do_resize": true,
   "do_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
   "image_mean": [
     0.5,
     0.5,
     0.5
   ],
-  "image_processor_type": "DonutImageProcessor",
   "image_std": [
     0.5,
     0.5,
@@ -18,9 +17,8 @@
   ],
   "processor_class": "DonutProcessor",
   "resample": 2,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 1280,
-    "width": 960
-  }
+  "size": [
+    960,
+    1280
+  ]
 }

tokenizer_config.json

@@ -1,6 +1,5 @@
 {
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
@@ -11,11 +10,12 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "naver-clova-ix/donut-base",
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }