End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-sroie
 
-This model is a fine-tuned version of [Assadullah/donut-base-sroie](https://huggingface.co/Assadullah/donut-base-sroie) 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
 
@@ -35,11 +35,11 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 2
-- eval_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.22.0.dev0
-- Pytorch 1.12.1+cu113
+- Transformers 4.23.0.dev0
+- Pytorch 1.8.1+cu102
 - Datasets 2.4.0
 - Tokenizers 0.12.1

preprocessor_config.json

@@ -18,7 +18,7 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "size": [
-    720,
-    960
+    360,
+    480
   ]
 }

runs/Sep21_00-26-37_0803-080200-elbow784-10-34-15-76/events.out.tfevents.1663721202.0803-080200-elbow784-10-34-15-76.1580.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf7b067e1ff97a867ad74434e021dc83331c5bcdb09d7d8b0465334e7bf88af
-size 9368
+oid sha256:50f1244426e02b4ee55add1d7f9ed3c6003d789bee54d1dda95a736dd557ec8d
+size 9722

tokenizer_config.json

@@ -10,7 +10,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "name_or_path": "Assadullah/donut-base-sroie",
+  "name_or_path": "naver-clova-ix/donut-base",
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",