End of training

README.md

@@ -1,10 +1,13 @@
 ---
 license: mit
-base_model: naver-clova-ix/donut-base
+base_model: davelotito/donut-base-sroie-test
 tags:
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- bleu
+- wer
 model-index:
 - name: donut-base-sroie-test
   results: []
@@ -15,7 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-sroie-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 [davelotito/donut-base-sroie-test](https://huggingface.co/davelotito/donut-base-sroie-test) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3913
+- Bleu: 0.0706
+- Precisions: [0.8125, 0.7440860215053764, 0.7064676616915423, 0.6637168141592921]
+- Brevity Penalty: 0.0968
+- Length Ratio: 0.2998
+- Translation Length: 528
+- Reference Length: 1761
+- Cer: 0.7448
+- Wer: 0.8259
 
 ## Model description
 
@@ -35,16 +48,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 32
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
+| No log        | 0.99  | 62   | 0.5515          | 0.0638 | [0.7647058823529411, 0.6831896551724138, 0.6309226932668329, 0.5857988165680473] | 0.0962          | 0.2993       | 527                | 1761             | 0.7627 | 0.8549 |
+| 0.5624        | 2.0   | 125  | 0.4773          | 0.0665 | [0.7763157894736842, 0.6865671641791045, 0.6403940886699507, 0.5918367346938775] | 0.0992          | 0.3021       | 532                | 1761             | 0.7562 | 0.8390 |
+| 0.5624        | 2.99  | 187  | 0.4273          | 0.0658 | [0.7840909090909091, 0.6903225806451613, 0.6517412935323383, 0.6047197640117994] | 0.0968          | 0.2998       | 528                | 1761             | 0.7513 | 0.8373 |
+| 0.2964        | 4.0   | 250  | 0.4007          | 0.0679 | [0.800376647834275, 0.7072649572649573, 0.6592592592592592, 0.6023391812865497]  | 0.0986          | 0.3015       | 531                | 1761             | 0.7478 | 0.8286 |
+| 0.2238        | 4.99  | 312  | 0.3965          | 0.0710 | [0.8142589118198874, 0.7297872340425532, 0.683046683046683, 0.6308139534883721]  | 0.0999          | 0.3027       | 533                | 1761             | 0.7427 | 0.8271 |
+| 0.2238        | 6.0   | 375  | 0.3939          | 0.0719 | [0.8301886792452831, 0.7537473233404711, 0.7054455445544554, 0.656891495601173]  | 0.0980          | 0.3010       | 530                | 1761             | 0.7414 | 0.8246 |
+| 0.147         | 6.99  | 437  | 0.3853          | 0.0693 | [0.8159392789373814, 0.7370689655172413, 0.6932668329177057, 0.6449704142011834] | 0.0962          | 0.2993       | 527                | 1761             | 0.7437 | 0.8237 |
+| 0.1316        | 8.0   | 500  | 0.3827          | 0.0698 | [0.8037735849056604, 0.7301927194860813, 0.6856435643564357, 0.6392961876832844] | 0.0980          | 0.3010       | 530                | 1761             | 0.7456 | 0.8296 |
+| 0.1316        | 8.99  | 562  | 0.3895          | 0.0704 | [0.8174904942965779, 0.7516198704103672, 0.715, 0.6706231454005934]              | 0.0956          | 0.2987       | 526                | 1761             | 0.7439 | 0.8259 |
+| 0.1153        | 9.92  | 620  | 0.3913          | 0.0706 | [0.8125, 0.7440860215053764, 0.7064676616915423, 0.6637168141592921]             | 0.0968          | 0.2998       | 528                | 1761             | 0.7448 | 0.8259 |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba58c87eff1b3f059314ec1b3b57f2599d02b70c395dd51563b0ac8e86f9d7c
+oid sha256:048fac7623cc1510a16cd7a9ba640a2f288f8e8dd0084c2f4e9f058aa8eeabf7
 size 809103512

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

@@ -1,75 +1,15 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<s_total>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s_total>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s_date>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s_date>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s_company>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s_company>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s_address>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s_address>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<s_total>",
+    "</s_total>",
+    "<s_date>",
+    "</s_date>",
+    "<s_company>",
+    "</s_company>",
+    "<s_address>",
+    "</s_address>",
+    "<s>",
+    "</s>"
   ],
   "bos_token": {
     "content": "<s>",

tokenizer_config.json

@@ -146,11 +146,18 @@
   "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>"
 }