End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: alexbeta80/donut-test
+base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-test
 
-This model is a fine-tuned version of [alexbeta80/donut-test](https://huggingface.co/alexbeta80/donut-test) on the imagefolder dataset.
+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.
 
 ## Model description
 
@@ -34,17 +34,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 2
+- learning_rate: 5e-06
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
-
-### Training results
-
-
+- num_epochs: 50
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "alexbeta80/donut-test",
+  "_name_or_path": "naver-clova-ix/donut-base",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],

generation_config.json

@@ -1,10 +1,8 @@
 {
   "_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": {
-    "height": 960,
-    "width": 720
-  }
+  "size": [
+    720,
+    960
+  ]
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c3b9a31f1e601e9c6e293768b33858819c1a6b38b2b7ddbc58a4f23d278a1c
+oid sha256:3f4e07ab41ceda7a98a8f9f0500a920bee562dac6db6a3607b007d0e1d6574e3
 size 809285846

special_tokens_map.json

@@ -1,10 +1,5 @@
 {
   "additional_special_tokens": [
-    "<s>",
-    "<pad>",
-    "</s>",
-    "<unk>",
-    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Total_Packages>",
@@ -21,12 +16,14 @@
     "</s_Consignee>",
     "<s_Second_Notify_Country>",
     "<s_Marks>",
+    "<s>",
     "<s_Total_Weight>",
     "</s_Notify>",
     "</s_Goods_Description>",
     "<s_Second_Notify>",
     "<s_Total_Volume>",
     "</s_Total_Weight>",
+    "</s>",
     "<s_Consignee>",
     "</s_Second_Notify>",
     "</s_Total_Volume>",

tokenizer_config.json

@@ -2,9 +2,9 @@
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -18,9 +18,9 @@
     },
     "2": {
       "content": "</s>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -35,7 +35,7 @@
     "57521": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -274,11 +274,6 @@
     }
   },
   "additional_special_tokens": [
-    "<s>",
-    "<pad>",
-    "</s>",
-    "<unk>",
-    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Total_Packages>",
@@ -295,12 +290,14 @@
     "</s_Consignee>",
     "<s_Second_Notify_Country>",
     "<s_Marks>",
+    "<s>",
     "<s_Total_Weight>",
     "</s_Notify>",
     "</s_Goods_Description>",
     "<s_Second_Notify>",
     "<s_Total_Volume>",
     "</s_Total_Weight>",
+    "</s>",
     "<s_Consignee>",
     "</s_Second_Notify>",
     "</s_Total_Volume>",
@@ -313,18 +310,11 @@
   "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>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9434c72ee9bed05405abc2c8f4f2d57aa138e300ccc2c01b9509f0f5630c4bca
+oid sha256:309e66b6aaf8a988285f29eaaabeaa7fb4f01ecf655dfe445354b2167aa6ce56
 size 4600