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: 0.9729
-- Answer: {'precision': 0.5061511423550088, 'recall': 0.7050183598531212, 'f1': 0.5892583120204603, 'number': 817}
-- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
-- Question: {'precision': 0.6674400618716164, 'recall': 0.8012999071494893, 'f1': 0.7282700421940929, 'number': 1077}
-- Overall Precision: 0.5840
-- Overall Recall: 0.7149
-- Overall F1: 0.6428
-- Overall Accuracy: 0.5953
+- Loss: 0.6139
+- Answer: {'precision': 0.8076923076923077, 'recall': 0.8739290085679314, 'f1': 0.8395061728395062, 'number': 817}
+- Header: {'precision': 0.3148148148148148, 'recall': 0.42857142857142855, 'f1': 0.36298932384341637, 'number': 119}
+- Question: {'precision': 0.796595744680851, 'recall': 0.8690807799442897, 'f1': 0.8312611012433393, 'number': 1077}
+- Overall Precision: 0.7659
+- Overall Recall: 0.8450
+- Overall F1: 0.8035
+- Overall Accuracy: 0.8009
 
 ## Model description
 
@@ -48,14 +48,13 @@ 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: 40
+- training_steps: 260
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                     | Header                                                      | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 1.5938        | 0.27  | 20   | 1.1884          | {'precision': 0.3494347379239466, 'recall': 0.41615667074663404, 'f1': 0.37988826815642457, 'number': 817} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4942455242966752, 'recall': 0.7177344475394615, 'f1': 0.5853843241196517, 'number': 1077} | 0.4387            | 0.5529         | 0.4892     | 0.5421           |
-| 1.1521        | 0.53  | 40   | 0.9729          | {'precision': 0.5061511423550088, 'recall': 0.7050183598531212, 'f1': 0.5892583120204603, 'number': 817}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.6674400618716164, 'recall': 0.8012999071494893, 'f1': 0.7282700421940929, 'number': 1077} | 0.5840            | 0.7149         | 0.6428     | 0.5953           |
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                   | Header                                                                                                     | Question                                                                                                 | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.7536        | 2.67  | 200  | 0.6139          | {'precision': 0.8076923076923077, 'recall': 0.8739290085679314, 'f1': 0.8395061728395062, 'number': 817} | {'precision': 0.3148148148148148, 'recall': 0.42857142857142855, 'f1': 0.36298932384341637, 'number': 119} | {'precision': 0.796595744680851, 'recall': 0.8690807799442897, 'f1': 0.8312611012433393, 'number': 1077} | 0.7659            | 0.8450         | 0.8035     | 0.8009           |
 
 
 ### Framework versions

logs/events.out.tfevents.1677026224.c4ac2e57e392.51574.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15db5f69a30a811251a80ec503bbd707124fa5fa031c87f983476a3d78041a37
-size 4914
+oid sha256:7cb9e73b8ddce86d8a1882750ea3aff9255ce5992ba96f0d20b41775c17af2be
+size 5268

logs/events.out.tfevents.1677031076.c4ac2e57e392.51574.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015225e6c077a04fd3c737f82a8f3328ad7058a1747ec1b68b5f0fd03737c01e
+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,