amresh564 commited on
Commit
75bcc4d
1 Parent(s): da4e2b9

Training in progress epoch 0

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/layoutlm-base-uncased
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: amresh564/layoutlm-funsd-tf
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # amresh564/layoutlm-funsd-tf
15
+
16
+ This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.6755
19
+ - Validation Loss: 1.4053
20
+ - Train Overall Precision: 0.1523
21
+ - Train Overall Recall: 0.2730
22
+ - Train Overall F1: 0.1955
23
+ - Train Overall Accuracy: 0.4103
24
+ - Epoch: 0
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
44
+ - training_precision: float32
45
+
46
+ ### Training results
47
+
48
+ | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
49
+ |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
50
+ | 1.6755 | 1.4053 | 0.1523 | 0.2730 | 0.1955 | 0.4103 | 0 |
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.38.1
56
+ - TensorFlow 2.15.0
57
+ - Datasets 2.18.0
58
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlm-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-HEADER",
13
+ "2": "I-HEADER",
14
+ "3": "B-QUESTION",
15
+ "4": "I-QUESTION",
16
+ "5": "B-ANSWER",
17
+ "6": "I-ANSWER"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "B-ANSWER": 5,
23
+ "B-HEADER": 1,
24
+ "B-QUESTION": 3,
25
+ "I-ANSWER": 6,
26
+ "I-HEADER": 2,
27
+ "I-QUESTION": 4,
28
+ "O": 0
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_2d_position_embeddings": 1024,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "layoutlm",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "transformers_version": "4.38.1",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30522
43
+ }
logs/train/events.out.tfevents.1709379476.7b15d2f9fd37.315.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0320105b6072674cc2f16667fc8da3b01b59671d70eb1578ac8edf7f6690a5
3
+ size 2364935
logs/validation/events.out.tfevents.1709380662.7b15d2f9fd37.315.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca318e1803a9ef17803994c4bc84df5e7019cccf3c97dc89649a14b7bf296328
3
+ size 231
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9dcea92dd53f020f4f75f3eb1d0b5107d9235df903d41f28befa45835b9b2c
3
+ size 450829256