End of training

README.md

@@ -1,13 +1,13 @@
 ---
 license: mit
-base_model: naver-clova-ix/donut-base
+base_model: davelotito/donut-base-sroie
 tags:
 - generated_from_trainer
 datasets:
 - imagefolder
 metrics:
 - bleu
-- rouge
+- wer
 model-index:
 - name: donut-base-sroie-v2
   results: []
@@ -18,18 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-sroie-v2
 
-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.
 It achieves the following results on the evaluation set:
-- Loss: 0.2767
-- Bleu: 0.0208
-- Precisions: [0.9802904564315352, 0.9578246392896781, 0.9331742243436754, 0.9045161290322581]
-- Brevity Penalty: 0.0221
-- Length Ratio: 0.2077
-- Translation Length: 964
-- Reference Length: 4641
-- Rouge: 0.2990
-- Gen Len: 20.0
-- Meteor: 0.0936
+- Loss: 0.4355
+- Bleu: 0.8879
+- Precisions: [0.943646408839779, 0.9119229045271179, 0.8854285064787452, 0.860009225092251]
+- Brevity Penalty: 0.9868
+- Length Ratio: 0.9869
+- Translation Length: 4525
+- Reference Length: 4585
+- Cer: 0.0857
+- Wer: 0.2978
 
 ## Model description
 
@@ -61,17 +60,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Rouge  | Gen Len | Meteor |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:-------:|:------:|
-| No log        | 0.99  | 62   | 0.3836          | 0.0204 | [0.9853709508881923, 0.9686800894854586, 0.950661853188929, 0.9296875]           | 0.0213          | 0.2062       | 957                | 4641             | 0.3040 | 20.0    | 0.0939 |
-| 0.0493        | 2.0   | 125  | 0.2654          | 0.0206 | [0.9823100936524454, 0.9621380846325167, 0.9413173652694611, 0.917098445595855]  | 0.0217          | 0.2071       | 961                | 4641             | 0.2996 | 20.0    | 0.0939 |
-| 0.0493        | 2.99  | 187  | 0.2727          | 0.0207 | [0.9823284823284824, 0.9621802002224694, 0.9401913875598086, 0.9146183699870634] | 0.0218          | 0.2073       | 962                | 4641             | 0.3007 | 20.0    | 0.0937 |
-| 0.0734        | 3.97  | 248  | 0.2767          | 0.0208 | [0.9802904564315352, 0.9578246392896781, 0.9331742243436754, 0.9045161290322581] | 0.0221          | 0.2077       | 964                | 4641             | 0.2990 | 20.0    | 0.0936 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
+| No log        | 0.99  | 62   | 0.4638          | 0.8823 | [0.9399823477493381, 0.9044528977399866, 0.8772128915115751, 0.8514851485148515] | 0.9884          | 0.9884       | 4532               | 4585             | 0.0912 | 0.3085 |
+| 0.0043        | 2.0   | 125  | 0.4421          | 0.8853 | [0.9405155320555189, 0.9059428060768543, 0.8794470881486517, 0.8537931034482759] | 0.9899          | 0.9900       | 4539               | 4585             | 0.0889 | 0.3050 |
+| 0.0043        | 2.99  | 187  | 0.4328          | 0.8904 | [0.9399122807017544, 0.9068267734044919, 0.8809201623815968, 0.8558682223747426] | 0.9945          | 0.9945       | 4560               | 4585             | 0.0842 | 0.2939 |
+| 0.0106        | 3.97  | 248  | 0.4355          | 0.8879 | [0.943646408839779, 0.9119229045271179, 0.8854285064787452, 0.860009225092251]   | 0.9868          | 0.9869       | 4525               | 4585             | 0.0857 | 0.2978 |
 
 
 ### Framework versions
 
-- Transformers 4.39.0.dev0
-- Pytorch 2.2.1+cu121
-- Datasets 2.17.1
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.0
+- Datasets 2.18.0
 - Tokenizers 0.15.2

generation_config.json

@@ -1,7 +1,9 @@
 {
   "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": "4.39.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ef1f024d1be6aead61edbdc17056f08496d889d819cfe6c633b4d0da05f677
+oid sha256:7504e3f46a16625564b7490aeef33fe0ae152340809953544ddb9ac2000e2631
 size 809070744

preprocessor_config.json

@@ -37,8 +37,8 @@
   "processor_class": "DonutProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "size": [
-    720,
-    960
-  ]
+  "size": {
+    "height": 960,
+    "width": 720
+  }
 }

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
   "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": {
     "content": "<s>",

tokenizer_config.json

@@ -66,19 +66,26 @@
     }
   },
   "additional_special_tokens": [
-    "<s>",
-    "</s>"
+    "</s>",
+    "<s>"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "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>"
 }