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 [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the funsd-layoutlmv3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4637
-- Answer: {'precision': 0.8445714285714285, 'recall': 0.9045287637698899, 'f1': 0.8735224586288417, 'number': 817}
-- Header: {'precision': 0.6271186440677966, 'recall': 0.6218487394957983, 'f1': 0.6244725738396625, 'number': 119}
-- Question: {'precision': 0.9180790960451978, 'recall': 0.9052924791086351, 'f1': 0.9116409537166901, 'number': 1077}
-- Overall Precision: 0.8701
-- Overall Recall: 0.8882
-- Overall F1: 0.8791
-- Overall Accuracy: 0.7969
+- Loss: 0.8293
+- Answer: {'precision': 0.8251986379114642, 'recall': 0.8898408812729498, 'f1': 0.8563015312131919, 'number': 817}
+- Header: {'precision': 0.46987951807228917, 'recall': 0.3277310924369748, 'f1': 0.38613861386138615, 'number': 119}
+- Question: {'precision': 0.852014010507881, 'recall': 0.903435468895079, 'f1': 0.8769716088328076, 'number': 1077}
+- Overall Precision: 0.8257
+- Overall Recall: 0.8639
+- Overall F1: 0.8444
+- Overall Accuracy: 0.8141
 
 ## Model description
 
@@ -48,15 +48,15 @@ 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
-- training_steps: 500
+- training_steps: 200
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                   | Header                                                                                                   | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.017         | 10.53 | 200  | 1.4637          | {'precision': 0.8445714285714285, 'recall': 0.9045287637698899, 'f1': 0.8735224586288417, 'number': 817} | {'precision': 0.6271186440677966, 'recall': 0.6218487394957983, 'f1': 0.6244725738396625, 'number': 119} | {'precision': 0.9180790960451978, 'recall': 0.9052924791086351, 'f1': 0.9116409537166901, 'number': 1077} | 0.8701            | 0.8882         | 0.8791     | 0.7969           |
-| 0.0025        | 21.05 | 400  | 1.5607          | {'precision': 0.8456140350877193, 'recall': 0.8849449204406364, 'f1': 0.8648325358851674, 'number': 817} | {'precision': 0.6296296296296297, 'recall': 0.5714285714285714, 'f1': 0.5991189427312775, 'number': 119} | {'precision': 0.8882931188561215, 'recall': 0.9229340761374187, 'f1': 0.9052823315118397, 'number': 1077} | 0.8573            | 0.8867         | 0.8718     | 0.8017           |
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                   | Header                                                                                                     | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.7356        | 5.26  | 100  | 0.6810          | {'precision': 0.8133484162895928, 'recall': 0.8800489596083231, 'f1': 0.8453850676072897, 'number': 817} | {'precision': 0.5333333333333333, 'recall': 0.2689075630252101, 'f1': 0.35754189944134074, 'number': 119}  | {'precision': 0.8194331983805668, 'recall': 0.9396471680594243, 'f1': 0.8754325259515571, 'number': 1077} | 0.8091            | 0.8758         | 0.8411     | 0.8040           |
+| 0.1783        | 10.53 | 200  | 0.8293          | {'precision': 0.8251986379114642, 'recall': 0.8898408812729498, 'f1': 0.8563015312131919, 'number': 817} | {'precision': 0.46987951807228917, 'recall': 0.3277310924369748, 'f1': 0.38613861386138615, 'number': 119} | {'precision': 0.852014010507881, 'recall': 0.903435468895079, 'f1': 0.8769716088328076, 'number': 1077}   | 0.8257            | 0.8639         | 0.8444     | 0.8141           |
 
 
 ### Framework versions

logs/events.out.tfevents.1678098950.e05df67055ec.8321.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e811c4c0b125d7ce3e6a2ff8319f7a5a67d67975e4cbccc087b428ee0517dd92
-size 5566
+oid sha256:f7d30e67bf1d3df41a84ff2860b93a83a0784e9c8737cbe186abd92afea009b3
+size 5920

logs/events.out.tfevents.1678099142.e05df67055ec.8321.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb3b64b4e85c8e1c6869defc021a237b84c008db0ce3396b629c657a5ca115a
+size 592

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,