End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # donut_finetuning_macif
 
 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: 0.0392
 
 ## Model description
 
@@ -43,6 +45,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0537        | 1.0   | 2552 | 0.0519          |
+| 0.0267        | 2.0   | 5104 | 0.0400          |
+| 0.0096        | 3.0   | 7656 | 0.0392          |
 
 
 ### Framework versions

added_tokens.json

@@ -1,9 +1,5 @@
 {
-  "</s_gt_parse>": 57526,
-  "</s_immatriculation>": 57528,
-  "<s_gt_parse>": 57525,
   "<s_iitcdip>": 57523,
-  "<s_immatriculation>": 57527,
   "<s_synthdog>": 57524,
   "<sep/>": 57522
 }

runs/Jul07_14-52-23_datascience-1-0-ml-g4dn-xlarge-b3e2c7fea00ae03f4a997be929d0/events.out.tfevents.1688741556.datascience-1-0-ml-g4dn-xlarge-b3e2c7fea00ae03f4a997be929d0.15876.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19032b4df0a75ead534bc397755e4440cd7ec09306cc5fdf3b48f597137936c
-size 21317
+oid sha256:3cd985f965ceb36b039bc42942c1628d29d4c844d3fffcaba9c5a01bddd6bea5
+size 21671

special_tokens_map.json

@@ -1,9 +1,5 @@
 {
   "additional_special_tokens": [
-    "<s_gt_parse>",
-    "</s_gt_parse>",
-    "<s_immatriculation>",
-    "</s_immatriculation>",
     "<s>",
     "</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,
@@ -88,42 +74,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 57525,
-      "content": "<s_gt_parse>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57526,
-      "content": "</s_gt_parse>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57527,
-      "content": "<s_immatriculation>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57528,
-      "content": "</s_immatriculation>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {