End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: naver-clova-ix/donut-base
+base_model: davelotito/donut-base-sroie
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +15,7 @@ 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 is a fine-tuned version of [davelotito/donut-base-sroie](https://huggingface.co/davelotito/donut-base-sroie) on the imagefolder dataset.
 
 ## Model description
 
@@ -38,9 +38,11 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### 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": "4.36.0.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
+  }
 }

special_tokens_map.json

@@ -1,23 +1,29 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "</s>",
+    "<s>"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -25,7 +31,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -74,11 +74,18 @@
   "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>"
 }