End of training

README.md

@@ -16,14 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0638
-- Answer: {'precision': 0.24285714285714285, 'recall': 0.21013597033374537, 'f1': 0.22531477799867464, 'number': 809}
-- Header: {'precision': 0.08695652173913043, 'recall': 0.01680672268907563, 'f1': 0.028169014084507043, 'number': 119}
-- Question: {'precision': 0.5682362330407024, 'recall': 0.6685446009389672, 'f1': 0.6143226919758413, 'number': 1065}
-- Overall Precision: 0.4474
-- Overall Recall: 0.4436
-- Overall F1: 0.4455
-- Overall Accuracy: 0.6424
+- Loss: 1.0643
+- Answer: {'precision': 0.384928716904277, 'recall': 0.4672435105067985, 'f1': 0.4221105527638191, 'number': 809}
+- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
+- Question: {'precision': 0.5277088502894954, 'recall': 0.5990610328638498, 'f1': 0.5611257695690414, 'number': 1065}
+- Overall Precision: 0.4583
+- Overall Recall: 0.5098
+- Overall F1: 0.4827
+- Overall Accuracy: 0.6395
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                      | Header                                                                                                       | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 1.4448        | 1.0   | 75   | 1.0638          | {'precision': 0.24285714285714285, 'recall': 0.21013597033374537, 'f1': 0.22531477799867464, 'number': 809} | {'precision': 0.08695652173913043, 'recall': 0.01680672268907563, 'f1': 0.028169014084507043, 'number': 119} | {'precision': 0.5682362330407024, 'recall': 0.6685446009389672, 'f1': 0.6143226919758413, 'number': 1065} | 0.4474            | 0.4436         | 0.4455     | 0.6424           |
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                  | Header                                                      | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.4286        | 1.0   | 75   | 1.0643          | {'precision': 0.384928716904277, 'recall': 0.4672435105067985, 'f1': 0.4221105527638191, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.5277088502894954, 'recall': 0.5990610328638498, 'f1': 0.5611257695690414, 'number': 1065} | 0.4583            | 0.5098         | 0.4827     | 0.6395           |
 
 
 ### Framework versions

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": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,