End of training

README.md

@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # donut-paper-ktp
 
 This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4558
 
 ## Model description
 
@@ -39,37 +37,17 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 15
+- lr_scheduler_type: linear
+- num_epochs: 9
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 46   | 6.4079          |
-| No log        | 2.0   | 92   | 3.8737          |
-| 7.1608        | 3.0   | 138  | 2.9063          |
-| 7.1608        | 4.0   | 184  | 0.9980          |
-| 2.4956        | 5.0   | 230  | 0.7675          |
-| 2.4956        | 6.0   | 276  | 0.6447          |
-| 0.7023        | 7.0   | 322  | 0.5472          |
-| 0.7023        | 8.0   | 368  | 0.4761          |
-| 0.3457        | 9.0   | 414  | 0.4361          |
-| 0.3457        | 10.0  | 460  | 0.4849          |
-| 0.1816        | 11.0  | 506  | 0.4623          |
-| 0.1816        | 12.0  | 552  | 0.4471          |
-| 0.1816        | 13.0  | 598  | 0.4514          |
-| 0.132         | 14.0  | 644  | 0.4546          |
-| 0.132         | 15.0  | 690  | 0.4558          |
 
 
 ### Framework versions
 
 - Transformers 4.52.4
 - Pytorch 2.6.0+cu124
-- Datasets 3.6.0
+- Datasets 4.0.0
 - Tokenizers 0.21.1

added_tokens.json

@@ -1,11 +1,11 @@
 {
-  "</s_agama>": 57558,
-  "</s_alamat>": 57556,
-  "</s_berlaku>": 57554,
-  "</s_gol_darah>": 57552,
-  "</s_jkel>": 57550,
-  "</s_kabkota_issuer>": 57548,
-  "</s_kecamatan>": 57546,
+  "</s_agama>": 57554,
+  "</s_alamat>": 57552,
+  "</s_berlaku>": 57558,
+  "</s_gol_darah>": 57550,
+  "</s_jkel>": 57548,
+  "</s_kabkota_issuer>": 57546,
+  "</s_kecamatan>": 57556,
   "</s_kelurahan>": 57544,
   "</s_nama>": 57542,
   "</s_nik>": 57540,
@@ -16,14 +16,14 @@
   "</s_tgl_terbit>": 57530,
   "</s_ttl>": 57528,
   "</s_wn>": 57526,
-  "<s_agama>": 57557,
-  "<s_alamat>": 57555,
-  "<s_berlaku>": 57553,
-  "<s_gol_darah>": 57551,
+  "<s_agama>": 57553,
+  "<s_alamat>": 57551,
+  "<s_berlaku>": 57557,
+  "<s_gol_darah>": 57549,
   "<s_iitcdip>": 57523,
-  "<s_jkel>": 57549,
-  "<s_kabkota_issuer>": 57547,
-  "<s_kecamatan>": 57545,
+  "<s_jkel>": 57547,
+  "<s_kabkota_issuer>": 57545,
+  "<s_kecamatan>": 57555,
   "<s_kelurahan>": 57543,
   "<s_nama>": 57541,
   "<s_nik>": 57539,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52a731a2477eab12508c7954da40a343e74f2c61f1b65da950bac8d68dd75ad
+oid sha256:dcedd6515fc84deccbd4f8b4f9ee0ae5f6125fadd0eedcbf4b46accac1a15eaf
 size 809210008

runs/Jul10_07-44-40_0fb90cc67b13/events.out.tfevents.1752133481.0fb90cc67b13.101.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1776385a4734bf0ee11d9864081b559ae8ea913851806b5e19a691decb5487d
-size 10636
+oid sha256:9c16c2615f2c6d0e7fcb987d0616b606880a6973f1e4e6d68e5fe0ee0e0c00e6
+size 11623

special_tokens_map.json

@@ -141,98 +141,98 @@
       "single_word": false
     },
     {
-      "content": "<s_kecamatan>",
+      "content": "<s_kabkota_issuer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_kecamatan>",
+      "content": "</s_kabkota_issuer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_kabkota_issuer>",
+      "content": "<s_jkel>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_kabkota_issuer>",
+      "content": "</s_jkel>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_jkel>",
+      "content": "<s_gol_darah>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_jkel>",
+      "content": "</s_gol_darah>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_gol_darah>",
+      "content": "<s_alamat>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_gol_darah>",
+      "content": "</s_alamat>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_berlaku>",
+      "content": "<s_agama>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_berlaku>",
+      "content": "</s_agama>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_alamat>",
+      "content": "<s_kecamatan>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_alamat>",
+      "content": "</s_kecamatan>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_agama>",
+      "content": "<s_berlaku>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "</s_agama>",
+      "content": "</s_berlaku>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -257,7 +271,7 @@
     },
     {
       "id": 57545,
-      "content": "<s_kecamatan>",
+      "content": "<s_kabkota_issuer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -266,7 +280,7 @@
     },
     {
       "id": 57546,
-      "content": "</s_kecamatan>",
+      "content": "</s_kabkota_issuer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -275,7 +289,7 @@
     },
     {
       "id": 57547,
-      "content": "<s_kabkota_issuer>",
+      "content": "<s_jkel>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -284,7 +298,7 @@
     },
     {
       "id": 57548,
-      "content": "</s_kabkota_issuer>",
+      "content": "</s_jkel>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -293,7 +307,7 @@
     },
     {
       "id": 57549,
-      "content": "<s_jkel>",
+      "content": "<s_gol_darah>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -302,7 +316,7 @@
     },
     {
       "id": 57550,
-      "content": "</s_jkel>",
+      "content": "</s_gol_darah>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -311,7 +325,7 @@
     },
     {
       "id": 57551,
-      "content": "<s_gol_darah>",
+      "content": "<s_alamat>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -320,7 +334,7 @@
     },
     {
       "id": 57552,
-      "content": "</s_gol_darah>",
+      "content": "</s_alamat>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -329,7 +343,7 @@
     },
     {
       "id": 57553,
-      "content": "<s_berlaku>",
+      "content": "<s_agama>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -338,7 +352,7 @@
     },
     {
       "id": 57554,
-      "content": "</s_berlaku>",
+      "content": "</s_agama>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -347,7 +361,7 @@
     },
     {
       "id": 57555,
-      "content": "<s_alamat>",
+      "content": "<s_kecamatan>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -356,7 +370,7 @@
     },
     {
       "id": 57556,
-      "content": "</s_alamat>",
+      "content": "</s_kecamatan>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -365,7 +379,7 @@
     },
     {
       "id": 57557,
-      "content": "<s_agama>",
+      "content": "<s_berlaku>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -374,7 +388,7 @@
     },
     {
       "id": 57558,
-      "content": "</s_agama>",
+      "content": "</s_berlaku>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -225,7 +225,7 @@
       "special": true
     },
     "57545": {
-      "content": "<s_kecamatan>",
+      "content": "<s_kabkota_issuer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -233,7 +233,7 @@
       "special": true
     },
     "57546": {
-      "content": "</s_kecamatan>",
+      "content": "</s_kabkota_issuer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -241,7 +241,7 @@
       "special": true
     },
     "57547": {
-      "content": "<s_kabkota_issuer>",
+      "content": "<s_jkel>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -249,7 +249,7 @@
       "special": true
     },
     "57548": {
-      "content": "</s_kabkota_issuer>",
+      "content": "</s_jkel>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -257,7 +257,7 @@
       "special": true
     },
     "57549": {
-      "content": "<s_jkel>",
+      "content": "<s_gol_darah>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -265,7 +265,7 @@
       "special": true
     },
     "57550": {
-      "content": "</s_jkel>",
+      "content": "</s_gol_darah>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -273,7 +273,7 @@
       "special": true
     },
     "57551": {
-      "content": "<s_gol_darah>",
+      "content": "<s_alamat>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -281,7 +281,7 @@
       "special": true
     },
     "57552": {
-      "content": "</s_gol_darah>",
+      "content": "</s_alamat>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -289,7 +289,7 @@
       "special": true
     },
     "57553": {
-      "content": "<s_berlaku>",
+      "content": "<s_agama>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -297,7 +297,7 @@
       "special": true
     },
     "57554": {
-      "content": "</s_berlaku>",
+      "content": "</s_agama>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -305,7 +305,7 @@
       "special": true
     },
     "57555": {
-      "content": "<s_alamat>",
+      "content": "<s_kecamatan>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -313,7 +313,7 @@
       "special": true
     },
     "57556": {
-      "content": "</s_alamat>",
+      "content": "</s_kecamatan>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -321,7 +321,7 @@
       "special": true
     },
     "57557": {
-      "content": "<s_agama>",
+      "content": "<s_berlaku>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -329,7 +329,7 @@
       "special": true
     },
     "57558": {
-      "content": "</s_agama>",
+      "content": "</s_berlaku>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -358,20 +358,20 @@
     "</s_nama>",
     "<s_kelurahan>",
     "</s_kelurahan>",
-    "<s_kecamatan>",
-    "</s_kecamatan>",
     "<s_kabkota_issuer>",
     "</s_kabkota_issuer>",
     "<s_jkel>",
     "</s_jkel>",
     "<s_gol_darah>",
     "</s_gol_darah>",
-    "<s_berlaku>",
-    "</s_berlaku>",
     "<s_alamat>",
     "</s_alamat>",
     "<s_agama>",
     "</s_agama>",
+    "<s_kecamatan>",
+    "</s_kecamatan>",
+    "<s_berlaku>",
+    "</s_berlaku>",
     "<s>",
     "</s>"
   ],