End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 1.8879
+- Loss: 0.3545
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.0437        | 1.0   | 50   | 4.3564          |
-| 3.6792        | 2.0   | 100  | 2.1457          |
-| 2.4216        | 3.0   | 150  | 1.8879          |
+| 1.853         | 1.0   | 100  | 0.5830          |
+| 0.6005        | 2.0   | 200  | 0.3953          |
+| 0.4386        | 3.0   | 300  | 0.3545          |
 
 
 ### Framework versions

added_tokens.json

@@ -1,22 +1,18 @@
 {
   "</s>": 2,
-  "</s_CODICI>": 57535,
-  "</s_DATA>": 57527,
-  "</s_FORNITORE>": 57532,
-  "</s_NUMERO>": 57531,
-  "</s_OGGETTI>": 57534,
-  "</s_POSIZIONI>": 57528,
-  "</s_QUANTITA>": 57529,
+  "</s_CODICE>": 57529,
+  "</s_CODICI>": 57532,
+  "</s_POSIZIONE>": 57528,
+  "</s_POSIZIONI>": 57525,
+  "</s_QUANTITA>": 57530,
   "<mask>": 57521,
   "<pad>": 1,
   "<s>": 0,
+  "<s_CODICE>": 57534,
   "<s_CODICI>": 57526,
-  "<s_DATA>": 57525,
-  "<s_FORNITORE>": 57530,
-  "<s_NUMERO>": 57538,
-  "<s_OGGETTI>": 57537,
-  "<s_POSIZIONI>": 57533,
-  "<s_QUANTITA>": 57536,
+  "<s_POSIZIONE>": 57527,
+  "<s_POSIZIONI>": 57531,
+  "<s_QUANTITA>": 57533,
   "<s_iitcdip>": 57523,
   "<s_synthdog>": 57524,
   "<sep/>": 57522,

config.json

@@ -85,7 +85,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57539
+    "vocab_size": 57535
   },
   "decoder_start_token_id": 0,
   "encoder": {

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6aebb4453933dfa8157ded0f7e7960339e0c8e89fd96cbeba31d257b809180
-size 809236694
+oid sha256:0f77222446b5baa5d59ff3f66bff13f80238b34b9923329aa69cbd0e96d14cec
+size 809220310

special_tokens_map.json

@@ -2,22 +2,18 @@
   "additional_special_tokens": [
     "<s_iitcdip>",
     "<s_synthdog>",
-    "<s_DATA>",
-    "<s_CODICI>",
-    "</s_DATA>",
     "</s_POSIZIONI>",
-    "<s>",
+    "<s_CODICI>",
     "</s>",
+    "<s_POSIZIONE>",
+    "</s_POSIZIONE>",
+    "</s_CODICE>",
     "</s_QUANTITA>",
-    "<s_FORNITORE>",
-    "</s_NUMERO>",
-    "</s_FORNITORE>",
     "<s_POSIZIONI>",
-    "</s_OGGETTI>",
     "</s_CODICI>",
     "<s_QUANTITA>",
-    "<s_OGGETTI>",
-    "<s_NUMERO>"
+    "<s_CODICE>",
+    "<s>"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "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>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -91,7 +77,7 @@
     },
     {
       "id": 57525,
-      "content": "<s_DATA>",
+      "content": "</s_POSIZIONI>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,
@@ -109,7 +95,7 @@
     },
     {
       "id": 57527,
-      "content": "</s_DATA>",
+      "content": "<s_POSIZIONE>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,
@@ -118,7 +104,7 @@
     },
     {
       "id": 57528,
-      "content": "</s_POSIZIONI>",
+      "content": "</s_POSIZIONE>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,
@@ -127,7 +113,7 @@
     },
     {
       "id": 57529,
-      "content": "</s_QUANTITA>",
+      "content": "</s_CODICE>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,
@@ -136,7 +122,7 @@
     },
     {
       "id": 57530,
-      "content": "<s_FORNITORE>",
+      "content": "</s_QUANTITA>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,
@@ -145,24 +131,6 @@
     },
     {
       "id": 57531,
-      "content": "</s_NUMERO>",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57532,
-      "content": "</s_FORNITORE>",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57533,
       "content": "<s_POSIZIONI>",
       "single_word": false,
       "lstrip": true,
@@ -171,16 +139,7 @@
       "special": true
     },
     {
-      "id": 57534,
-      "content": "</s_OGGETTI>",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57535,
+      "id": 57532,
       "content": "</s_CODICI>",
       "single_word": false,
       "lstrip": true,
@@ -189,7 +148,7 @@
       "special": true
     },
     {
-      "id": 57536,
+      "id": 57533,
       "content": "<s_QUANTITA>",
       "single_word": false,
       "lstrip": true,
@@ -198,17 +157,8 @@
       "special": true
     },
     {
-      "id": 57537,
-      "content": "<s_OGGETTI>",
-      "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57538,
-      "content": "<s_NUMERO>",
+      "id": 57534,
+      "content": "<s_CODICE>",
       "single_word": false,
       "lstrip": true,
       "rstrip": true,

tokenizer_config.json

@@ -65,7 +65,7 @@
       "special": true
     },
     "57525": {
-      "content": "<s_DATA>",
+      "content": "</s_POSIZIONI>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -81,7 +81,7 @@
       "special": true
     },
     "57527": {
-      "content": "</s_DATA>",
+      "content": "<s_POSIZIONE>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -89,7 +89,7 @@
       "special": true
     },
     "57528": {
-      "content": "</s_POSIZIONI>",
+      "content": "</s_POSIZIONE>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -97,7 +97,7 @@
       "special": true
     },
     "57529": {
-      "content": "</s_QUANTITA>",
+      "content": "</s_CODICE>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -105,7 +105,7 @@
       "special": true
     },
     "57530": {
-      "content": "<s_FORNITORE>",
+      "content": "</s_QUANTITA>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -113,22 +113,6 @@
       "special": true
     },
     "57531": {
-      "content": "</s_NUMERO>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "57532": {
-      "content": "</s_FORNITORE>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "57533": {
       "content": "<s_POSIZIONI>",
       "lstrip": true,
       "normalized": false,
@@ -136,15 +120,7 @@
       "single_word": false,
       "special": true
     },
-    "57534": {
-      "content": "</s_OGGETTI>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "57535": {
+    "57532": {
       "content": "</s_CODICI>",
       "lstrip": true,
       "normalized": false,
@@ -152,7 +128,7 @@
       "single_word": false,
       "special": true
     },
-    "57536": {
+    "57533": {
       "content": "<s_QUANTITA>",
       "lstrip": true,
       "normalized": false,
@@ -160,16 +136,8 @@
       "single_word": false,
       "special": true
     },
-    "57537": {
-      "content": "<s_OGGETTI>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "57538": {
-      "content": "<s_NUMERO>",
+    "57534": {
+      "content": "<s_CODICE>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
@@ -180,22 +148,18 @@
   "additional_special_tokens": [
     "<s_iitcdip>",
     "<s_synthdog>",
-    "<s_DATA>",
-    "<s_CODICI>",
-    "</s_DATA>",
     "</s_POSIZIONI>",
-    "<s>",
+    "<s_CODICI>",
     "</s>",
+    "<s_POSIZIONE>",
+    "</s_POSIZIONE>",
+    "</s_CODICE>",
     "</s_QUANTITA>",
-    "<s_FORNITORE>",
-    "</s_NUMERO>",
-    "</s_FORNITORE>",
     "<s_POSIZIONI>",
-    "</s_OGGETTI>",
     "</s_CODICI>",
     "<s_QUANTITA>",
-    "<s_OGGETTI>",
-    "<s_NUMERO>"
+    "<s_CODICE>",
+    "<s>"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a735dac94e68727f3a9b7e6cad599d4554366548680fba70beb659366f1135
+oid sha256:d66378bc8123f196b8ea02123a5a19a9dadb9f54daad125e8e98ce9d42886957
 size 4664