End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: naver-clova-ix/donut-base
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Assignment
 
-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.
 
 ## Model description
 
@@ -34,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 25
+- num_epochs: 10
 
 ### 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": "4.32.0.dev0"
 }

preprocessor_config.json

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

tokenizer_config.json

@@ -11,11 +11,18 @@
     "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>"
 }