layoutlmv3-finetuned-cord_100

README.md

@@ -0,0 +1,99 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+datasets:
+- cord-layoutlmv3
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: layoutlmv3-finetuned-cord_100
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: cord-layoutlmv3
+      type: cord-layoutlmv3
+      config: cord
+      split: test
+      args: cord
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9458456973293768
+    - name: Recall
+      type: recall
+      value: 0.9543413173652695
+    - name: F1
+      type: f1
+      value: 0.9500745156482863
+    - name: Accuracy
+      type: accuracy
+      value: 0.9596774193548387
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# layoutlmv3-finetuned-cord_100
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2123
+- Precision: 0.9458
+- Recall: 0.9543
+- F1: 0.9501
+- Accuracy: 0.9597
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 2500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.56  | 250  | 1.0095          | 0.7120    | 0.7754 | 0.7424 | 0.7946   |
+| 1.3738        | 3.12  | 500  | 0.5732          | 0.8473    | 0.8683 | 0.8577 | 0.8714   |
+| 1.3738        | 4.69  | 750  | 0.3840          | 0.8893    | 0.9079 | 0.8985 | 0.9181   |
+| 0.4085        | 6.25  | 1000 | 0.2933          | 0.9181    | 0.9319 | 0.9250 | 0.9376   |
+| 0.4085        | 7.81  | 1250 | 0.2704          | 0.9197    | 0.9349 | 0.9272 | 0.9444   |
+| 0.2239        | 9.38  | 1500 | 0.2504          | 0.9369    | 0.9454 | 0.9411 | 0.9508   |
+| 0.2239        | 10.94 | 1750 | 0.2375          | 0.9288    | 0.9379 | 0.9333 | 0.9465   |
+| 0.1544        | 12.5  | 2000 | 0.2326          | 0.9423    | 0.9528 | 0.9475 | 0.9576   |
+| 0.1544        | 14.06 | 2250 | 0.2147          | 0.9530    | 0.9566 | 0.9548 | 0.9610   |
+| 0.1231        | 15.62 | 2500 | 0.2123          | 0.9458    | 0.9543 | 0.9501 | 0.9597   |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1