End of training

README.md

@@ -14,20 +14,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Footer: {'precision': 0.9749447310243183, 'recall': 0.9792746113989638, 'f1': 0.9771048744460857, 'number': 1351}
-- Header: {'precision': 0.927519818799547, 'recall': 0.9578947368421052, 'f1': 0.9424626006904488, 'number': 855}
-- Able: {'precision': 0.7589285714285714, 'recall': 0.8531994981179423, 'f1': 0.8033077377436504, 'number': 797}
-- Aption: {'precision': 0.6352785145888594, 'recall': 0.7496087636932708, 'f1': 0.687724335965542, 'number': 639}
-- Ext: {'precision': 0.6819444444444445, 'recall': 0.7897064736630478, 'f1': 0.7318800074529532, 'number': 2487}
-- Icture: {'precision': 0.772196261682243, 'recall': 0.8283208020050126, 'f1': 0.7992744860943168, 'number': 798}
-- Itle: {'precision': 0.4519230769230769, 'recall': 0.415929203539823, 'f1': 0.43317972350230416, 'number': 113}
-- Ootnote: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 55}
-- Ormula: {'precision': 0.38578680203045684, 'recall': 0.7307692307692307, 'f1': 0.5049833887043189, 'number': 104}
-- Overall Precision: 0.7631
-- Overall Recall: 0.8403
-- Overall F1: 0.7998
-- Overall Accuracy: 0.9572
+- Loss: 1.4071
+- Footer: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186}
+- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373}
+- Able: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100}
+- Aption: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148}
+- Ext: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566}
+- Icture: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270}
+- Itle: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45}
+- Ootnote: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8}
+- Overall Precision: 0.0
+- Overall Recall: 0.0
+- Overall F1: 0.0
+- Overall Accuracy: 0.6399
 
 ## Model description
 
@@ -47,19 +46,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 2
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Footer                                                                                                    | Header                                                                                                  | Able                                                                                                     | Aption                                                                                                   | Ext                                                                                                       | Icture                                                                                                   | Itle                                                                                                        | Ootnote                                                    | Ormula                                                                                                     | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.6151        | 1.0   | 4900 | nan             | {'precision': 0.9154334038054969, 'recall': 0.9615099925980755, 'f1': 0.9379061371841154, 'number': 1351} | {'precision': 0.8517316017316018, 'recall': 0.92046783625731, 'f1': 0.8847667228780213, 'number': 855}  | {'precision': 0.5285592497868713, 'recall': 0.7779171894604768, 'f1': 0.6294416243654822, 'number': 797} | {'precision': 0.3216326530612245, 'recall': 0.6165884194053208, 'f1': 0.4227467811158798, 'number': 639} | {'precision': 0.4335355763927192, 'recall': 0.632086851628468, 'f1': 0.5143137575658433, 'number': 2487}  | {'precision': 0.5630585898709036, 'recall': 0.7105263157894737, 'f1': 0.6282548476454293, 'number': 798} | {'precision': 0.06504065040650407, 'recall': 0.21238938053097345, 'f1': 0.09958506224066391, 'number': 113} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 55} | {'precision': 0.07069408740359898, 'recall': 0.5288461538461539, 'f1': 0.12471655328798187, 'number': 104} | 0.5055            | 0.7387         | 0.6002     | 0.9093           |
-| 0.2733        | 2.0   | 9800 | nan             | {'precision': 0.9749447310243183, 'recall': 0.9792746113989638, 'f1': 0.9771048744460857, 'number': 1351} | {'precision': 0.927519818799547, 'recall': 0.9578947368421052, 'f1': 0.9424626006904488, 'number': 855} | {'precision': 0.7589285714285714, 'recall': 0.8531994981179423, 'f1': 0.8033077377436504, 'number': 797} | {'precision': 0.6352785145888594, 'recall': 0.7496087636932708, 'f1': 0.687724335965542, 'number': 639}  | {'precision': 0.6819444444444445, 'recall': 0.7897064736630478, 'f1': 0.7318800074529532, 'number': 2487} | {'precision': 0.772196261682243, 'recall': 0.8283208020050126, 'f1': 0.7992744860943168, 'number': 798}  | {'precision': 0.4519230769230769, 'recall': 0.415929203539823, 'f1': 0.43317972350230416, 'number': 113}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 55} | {'precision': 0.38578680203045684, 'recall': 0.7307692307692307, 'f1': 0.5049833887043189, 'number': 104}  | 0.7631            | 0.8403         | 0.7998     | 0.9572           |
+| Training Loss | Epoch | Step | Validation Loss | Footer                                                      | Header                                                      | Able                                                        | Aption                                                      | Ext                                                         | Icture                                                      | Itle                                                       | Ootnote                                                   | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:----------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.1724        | 1.0   | 1950 | 1.4537          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
+| 1.2004        | 2.0   | 3900 | 1.4094          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
+| 1.2026        | 3.0   | 5850 | 1.4038          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
+| 1.2107        | 4.0   | 7800 | 1.4217          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
+| 1.1836        | 5.0   | 9750 | 1.4071          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
 
 
 ### Framework versions

logs/events.out.tfevents.1679302770.138-2-233-57.311419.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3215211e58ba83f1a4e2024089b0884c1b58ad6184224e2971e97349c4b94eee
-size 7919
+oid sha256:55c631d919c5343a8bffa890c26d89e461532b0d72ad444cbac321fb0f8ae64a
+size 8273

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4477470206a7b460dc357ae8d3de93c05b6a692225c952341f50cb305f48d3e4
+oid sha256:b917c291ab5e4524bcedfe9de55f39e1df5d6eaf32649da86d74e156677bce9a
 size 503781199