End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: naver-clova-ix/donut-base
+base_model: alexbeta80/donut-test
 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 [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
+This model is a fine-tuned version of [alexbeta80/donut-test](https://huggingface.co/alexbeta80/donut-test) on the imagefolder dataset.
 
 ## Model description
 
@@ -40,7 +40,7 @@ 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: 1
+- num_epochs: 3
 
 ### Training results
 

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": [
-    720,
-    960
-  ]
+  "size": {
+    "height": 960,
+    "width": 720
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b9b2c3614e2e9b2cc3c6375104f4313ac0f270e0db4f31623be4f20dc25942
+oid sha256:fdbdb19db5b977f3aca73e6e59fb64929e79a9b4d7664c20394634b0344819f6
 size 809285846

special_tokens_map.json

@@ -1,5 +1,10 @@
 {
   "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Total_Packages>",
@@ -16,14 +21,12 @@
     "</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": 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
@@ -274,6 +274,11 @@
     }
   },
   "additional_special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<mask>",
     "<s_iitcdip>",
     "<s_synthdog>",
     "<s_Total_Packages>",
@@ -290,14 +295,12 @@
     "</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>",
@@ -310,11 +313,18 @@
   "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>"
 }