layoutlmv3-drc-id_trained

README.md

@@ -3,8 +3,6 @@ license: cc-by-nc-sa-4.0
 base_model: microsoft/layoutlmv3-base
 tags:
 - generated_from_trainer
-datasets:
-- funsd-layoutlmv3
 metrics:
 - precision
 - recall
@@ -12,29 +10,7 @@ metrics:
 - accuracy
 model-index:
 - name: test
-  results:
-  - task:
-      name: Token Classification
-      type: token-classification
-    dataset:
-      name: funsd-layoutlmv3
-      type: funsd-layoutlmv3
-      config: funsd
-      split: test
-      args: funsd
-    metrics:
-    - name: Precision
-      type: precision
-      value: 0.888781896966779
-    - name: Recall
-      type: recall
-      value: 0.9170392449080974
-    - name: F1
-      type: f1
-      value: 0.9026894865525672
-    - name: Accuracy
-      type: accuracy
-      value: 0.8572447402828955
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test
 
-This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the funsd-layoutlmv3 dataset.
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6019
-- Precision: 0.8888
-- Recall: 0.9170
-- F1: 0.9027
-- Accuracy: 0.8572
+- Loss: 0.2614
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9778
 
 ## Model description
 
@@ -73,22 +49,17 @@ 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: 1000
+- training_steps: 100
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.33  | 100  | 0.6846          | 0.7562    | 0.7874 | 0.7715 | 0.7729   |
-| No log        | 2.67  | 200  | 0.5002          | 0.8202    | 0.8818 | 0.8499 | 0.8433   |
-| No log        | 4.0   | 300  | 0.4580          | 0.8373    | 0.8847 | 0.8604 | 0.8556   |
-| No log        | 5.33  | 400  | 0.4812          | 0.8526    | 0.9106 | 0.8806 | 0.8416   |
-| 0.5581        | 6.67  | 500  | 0.4664          | 0.8768    | 0.9011 | 0.8888 | 0.8588   |
-| 0.5581        | 8.0   | 600  | 0.5033          | 0.8774    | 0.9136 | 0.8951 | 0.8607   |
-| 0.5581        | 9.33  | 700  | 0.5450          | 0.8757    | 0.9131 | 0.8940 | 0.8540   |
-| 0.5581        | 10.67 | 800  | 0.6086          | 0.8885    | 0.9106 | 0.8994 | 0.8590   |
-| 0.5581        | 12.0  | 900  | 0.5942          | 0.8885    | 0.9141 | 0.9011 | 0.8588   |
-| 0.1353        | 13.33 | 1000 | 0.6019          | 0.8888    | 0.9170 | 0.9027 | 0.8572   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 10.0  | 20   | 0.2566          | 0.0       | 0.0    | 0.0 | 0.9778   |
+| No log        | 20.0  | 40   | 0.2557          | 0.0       | 0.0    | 0.0 | 0.9778   |
+| No log        | 30.0  | 60   | 0.2579          | 0.0       | 0.0    | 0.0 | 0.9778   |
+| No log        | 40.0  | 80   | 0.2610          | 0.0       | 0.0    | 0.0 | 0.9778   |
+| No log        | 50.0  | 100  | 0.2614          | 0.0       | 0.0    | 0.0 | 0.9778   |
 
 
 ### Framework versions

config.json

@@ -14,25 +14,17 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "O",
-    "1": "B-HEADER",
-    "2": "I-HEADER",
-    "3": "B-QUESTION",
-    "4": "I-QUESTION",
-    "5": "B-ANSWER",
-    "6": "I-ANSWER"
+    "0": 0,
+    "1": 1,
+    "2": 2
   },
   "initializer_range": 0.02,
   "input_size": 224,
   "intermediate_size": 3072,
   "label2id": {
-    "B-ANSWER": 5,
-    "B-HEADER": 1,
-    "B-QUESTION": 3,
-    "I-ANSWER": 6,
-    "I-HEADER": 2,
-    "I-QUESTION": 4,
-    "O": 0
+    "0": 0,
+    "1": 1,
+    "2": 2
   },
   "layer_norm_eps": 1e-05,
   "max_2d_position_embeddings": 1024,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff317bcbea5f11c81662d92f48c7b6a4356598159d8959904f4529656c3c5a8
-size 501403301
+oid sha256:96bd05de1a3a14e26a522bd88f1202bf8ac022e5ccfaf251b93ea7c3140d5818
+size 501391013

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a65992e4f884cd52a8d7245f7cab4785c368880347b3e28a27888b040fdfa9
+oid sha256:feef112372ca4d21371e6b3927518f755e90bea374fb71dbb62ff706b4584fb8
 size 4027