mychen76/donut-receipt_v3

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
-datasets:
-- imagefolder
 model-index:
 - name: donut-receipt_v3
   results: []
@@ -15,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-receipt_v3
 
-This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3299
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on an unknown dataset.
 
 ## Model description
 
@@ -37,7 +33,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 3
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

added_tokens.json

@@ -1,13 +1,39 @@
 {
-  "</s_address>": 57532,
-  "</s_company>": 57530,
-  "</s_date>": 57528,
+  "</s_date>": 57558,
+  "</s_ignore>": 57556,
+  "</s_item_key>": 57554,
+  "</s_item_name>": 57552,
+  "</s_item_quantity>": 57550,
+  "</s_item_value>": 57548,
+  "</s_line_items>": 57546,
+  "</s_others>": 57542,
+  "</s_store_addr>": 57540,
+  "</s_store_name>": 57538,
+  "</s_subtotal>": 57536,
+  "</s_tax>": 57534,
+  "</s_telephone>": 57532,
+  "</s_text>": 57544,
+  "</s_time>": 57530,
+  "</s_tips>": 57528,
   "</s_total>": 57526,
-  "<s_address>": 57531,
-  "<s_company>": 57529,
-  "<s_date>": 57527,
+  "<s_date>": 57557,
+  "<s_ignore>": 57555,
   "<s_iitcdip>": 57523,
+  "<s_item_key>": 57553,
+  "<s_item_name>": 57551,
+  "<s_item_quantity>": 57549,
+  "<s_item_value>": 57547,
+  "<s_line_items>": 57545,
+  "<s_others>": 57541,
+  "<s_store_addr>": 57539,
+  "<s_store_name>": 57537,
+  "<s_subtotal>": 57535,
   "<s_synthdog>": 57524,
+  "<s_tax>": 57533,
+  "<s_telephone>": 57531,
+  "<s_text>": 57543,
+  "<s_time>": 57529,
+  "<s_tips>": 57527,
   "<s_total>": 57525,
   "<sep/>": 57522
 }

config.json

@@ -85,7 +85,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57533
+    "vocab_size": 57559
   },
   "decoder_start_token_id": 0,
   "encoder": {
@@ -124,8 +124,8 @@
       "1": "LABEL_1"
     },
     "image_size": [
-      1280,
-      960
+      960,
+      720
     ],
     "initializer_range": 0.02,
     "is_decoder": false,

generation_config.json

@@ -3,7 +3,7 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
-  "max_length": 720,
+  "max_length": 768,
   "pad_token_id": 1,
   "transformers_version": "4.34.0.dev0"
 }

preprocessor_config.json

@@ -19,8 +19,8 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 960,
-    "width": 720
-  }
+  "size": [
+    960,
+    720
+  ]
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adac532db99dcd72e3b44c6835516ac772f1135ec7ff4cd157cab965fd4f4231
-size 809211673
+oid sha256:5b2056ff6e22914837b730a821695396ad266d95750adc030972723c1ee9c06b
+size 809318169

special_tokens_map.json

@@ -2,12 +2,38 @@
   "additional_special_tokens": [
     "<s_total>",
     "</s_total>",
+    "<s_tips>",
+    "</s_tips>",
+    "<s_time>",
+    "</s_time>",
+    "<s_telephone>",
+    "</s_telephone>",
+    "<s_tax>",
+    "</s_tax>",
+    "<s_subtotal>",
+    "</s_subtotal>",
+    "<s_store_name>",
+    "</s_store_name>",
+    "<s_store_addr>",
+    "</s_store_addr>",
+    "<s_others>",
+    "</s_others>",
+    "<s_text>",
+    "</s_text>",
+    "<s_line_items>",
+    "</s_line_items>",
+    "<s_item_value>",
+    "</s_item_value>",
+    "<s_item_quantity>",
+    "</s_item_quantity>",
+    "<s_item_name>",
+    "</s_item_name>",
+    "<s_item_key>",
+    "</s_item_key>",
+    "<s_ignore>",
+    "</s_ignore>",
     "<s_date>",
     "</s_date>",
-    "<s_company>",
-    "</s_company>",
-    "<s_address>",
-    "</s_address>",
     "<s>",
     "</s>"
   ],

tokenizer_config.json

@@ -11,18 +11,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "max_length": 512,
   "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>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bfc74ed50a2a9ecca5fd558a26ac3f1bebc494e403066fe8490111ee94e213
+oid sha256:37c92230417edb0b83fd852b0e8071ec1b87ea49c61337458217bd243c226888
 size 4283