End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
 model-index:
@@ -45,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.30.2
-- Pytorch 2.1.0+cu118
-- Datasets 2.12.0
-- Tokenizers 0.13.3
+- Transformers 4.36.0
+- Pytorch 2.0.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.36.0"
 }

special_tokens_map.json

@@ -1,7 +1,19 @@
 {
   "additional_special_tokens": [
-    "<s>",
-    "</s>"
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer.json

@@ -109,7 +109,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -195,7 +196,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",
@@ -230289,6 +230291,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,16 +1,79 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "</s>",
+    "<s>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",