End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-sroie
 
-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.
+This model was trained from scratch on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.6913
+- Loss: 5.7016
 
 ## Model description
 
@@ -42,18 +40,37 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 25
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 18.9088       | 1.0   | 3    | 18.3757         |
-| 14.9604       | 2.0   | 6    | 12.0340         |
-| 12.7281       | 3.0   | 9    | 11.9031         |
-| 10.6777       | 4.0   | 12   | 9.9294          |
-| 10.1939       | 5.0   | 15   | 10.0405         |
-| 9.9764        | 6.0   | 18   | 9.6913          |
+| 9.5672        | 1.0   | 3    | 8.6900          |
+| 9.2165        | 2.0   | 6    | 8.1679          |
+| 8.6254        | 3.0   | 9    | 8.8826          |
+| 8.5961        | 4.0   | 12   | 7.9094          |
+| 8.0975        | 5.0   | 15   | 7.6390          |
+| 8.0688        | 6.0   | 18   | 7.3710          |
+| 7.8179        | 7.0   | 21   | 7.1756          |
+| 7.4056        | 8.0   | 24   | 7.1199          |
+| 7.2254        | 9.0   | 27   | 6.8964          |
+| 7.1395        | 10.0  | 30   | 6.8406          |
+| 7.2451        | 11.0  | 33   | 6.5694          |
+| 6.8052        | 12.0  | 36   | 6.7802          |
+| 6.8587        | 13.0  | 39   | 6.3983          |
+| 6.6803        | 14.0  | 42   | 6.3614          |
+| 6.5832        | 15.0  | 45   | 6.2045          |
+| 6.3016        | 16.0  | 48   | 6.3187          |
+| 6.3266        | 17.0  | 51   | 6.1394          |
+| 6.2154        | 18.0  | 54   | 5.9751          |
+| 6.0545        | 19.0  | 57   | 5.9170          |
+| 6.0753        | 20.0  | 60   | 5.9828          |
+| 6.0034        | 21.0  | 63   | 5.9600          |
+| 6.0545        | 22.0  | 66   | 5.8052          |
+| 5.8055        | 23.0  | 69   | 5.7358          |
+| 5.7705        | 24.0  | 72   | 5.6998          |
+| 5.8007        | 25.0  | 75   | 5.7016          |
 
 
 ### Framework versions

generation_config.json

@@ -1,8 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
+  "decoder_start_token_id": 0,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
+  "max_length": 512,
   "pad_token_id": 1,
   "transformers_version": "4.34.0"
 }

preprocessor_config.json

@@ -19,8 +19,8 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "size": [
-    800,
-    1200
-  ]
+  "size": {
+    "height": 1200,
+    "width": 800
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1afa8c8cba314946c29f1a854b129e38f31efbc8f7c3f1bc734be8a720a03d5
+oid sha256:ee195ff3b9c28b6512294616a99331bd2bff815135213f4a34377c79f4baa30d
 size 810743577

special_tokens_map.json

@@ -1,5 +1,10 @@
 {
   "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Ignore_9>",
@@ -84,7 +89,6 @@
     "</s_mother_nationalty_1>",
     "<s_child_middle_name_2>",
     "<s_Ignore_149>",
-    "<s>",
     "<s_Ignore_82>",
     "</s_Ignore_59>",
     "<s_father_religion_2>",
@@ -150,7 +154,6 @@
     "<s_Ignore_111>",
     "<s_Ignore_92>",
     "<s_Ignore_61>",
-    "</s>",
     "</s_Ignore_112>",
     "</s_Ignore_84>",
     "</s_Ignore_63>",

tokenizer_config.json

@@ -2,9 +2,9 @@
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -18,9 +18,9 @@
     },
     "2": {
       "content": "</s>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -35,7 +35,7 @@
     "57521": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -3122,6 +3122,11 @@
     }
   },
   "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Ignore_9>",
@@ -3206,7 +3211,6 @@
     "</s_mother_nationalty_1>",
     "<s_child_middle_name_2>",
     "<s_Ignore_149>",
-    "<s>",
     "<s_Ignore_82>",
     "</s_Ignore_59>",
     "<s_father_religion_2>",
@@ -3272,7 +3276,6 @@
     "<s_Ignore_111>",
     "<s_Ignore_92>",
     "<s_Ignore_61>",
-    "</s>",
     "</s_Ignore_112>",
     "</s_Ignore_84>",
     "</s_Ignore_63>",
@@ -3514,11 +3517,18 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "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>"
 }