End of training

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
@@ -51,4 +51,4 @@ The following hyperparameters were used during training:
 - Transformers 4.34.0.dev0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.0

added_tokens.json

@@ -1,13 +1,5 @@
 {
-  "</s_address>": 57532,
-  "</s_company>": 57530,
-  "</s_date>": 57528,
-  "</s_total>": 57526,
-  "<s_address>": 57531,
-  "<s_company>": 57529,
-  "<s_date>": 57527,
   "<s_iitcdip>": 57523,
   "<s_synthdog>": 57524,
-  "<s_total>": 57525,
   "<sep/>": 57522
 }

special_tokens_map.json

@@ -1,26 +1,14 @@
 {
   "additional_special_tokens": [
-    "<s_total>",
-    "</s_total>",
-    "<s_date>",
-    "</s_date>",
-    "<s_company>",
-    "</s_company>",
-    "<s_address>",
-    "</s_address>",
-    "<s>",
-    "</s>"
+    "<s_iitcdip>",
+    "<s_synthdog>",
+    "</s>",
+    "<s>"
   ],
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -21,8 +21,8 @@
       "id": 0,
       "content": "<s>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -39,8 +39,8 @@
       "id": 2,
       "content": "</s>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -66,8 +66,8 @@
       "id": 57522,
       "content": "<sep/>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": true,
       "special": false
     },
@@ -75,8 +75,8 @@
       "id": 57523,
       "content": "<s_iitcdip>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -84,80 +84,8 @@
       "id": 57524,
       "content": "<s_synthdog>",
       "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57525,
-      "content": "<s_total>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57526,
-      "content": "</s_total>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57527,
-      "content": "<s_date>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57528,
-      "content": "</s_date>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57529,
-      "content": "<s_company>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57530,
-      "content": "</s_company>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57531,
-      "content": "<s_address>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 57532,
-      "content": "</s_address>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
+      "lstrip": true,
+      "rstrip": true,
       "normalized": false,
       "special": true
     }
@@ -230361,6 +230289,7 @@
         "<mask>",
         0.0
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1,16 +1,81 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>",
+    "</s>",
+    "<s>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "DonutProcessor",