Hugging Face's logo

bhargavshivashankar
/
layoutlmv3-finetuned-cord_100

Token Classification
Transformers
TensorBoard
Safetensors
layoutlmv3
Generated from Trainer
Model card Files
xet
Metrics Community
bhargavshivashankar commited on
Commit
128593f
·
verified ·
1 Parent(s): f72d6ca

layoutlmv3-finetuned-cord_100

Browse files
Files changed (4) hide show
  1. README.md +12 -18
  2. model.safetensors +1 -1
  3. runs/Jan02_09-56-45_117a15486a19/events.out.tfevents.1735811814.117a15486a19.1160.0 +3 -0
  4. training_args.bin +2 -2
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.1047
25
- - Precision: 0.9013
26
- - Recall: 0.9076
27
- - F1: 0.9045
28
- - Accuracy: 0.8536
29
 
30
  ## Model description
31
 
@@ -45,27 +45,21 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
- - train_batch_size: 5
49
- - eval_batch_size: 5
50
  - seed: 42
51
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
- - training_steps: 2500
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | No log | 8.3333 | 250 | 0.5292 | 0.8805 | 0.8932 | 0.8868 | 0.8508 |
60
- | 0.3785 | 16.6667 | 500 | 0.6962 | 0.8737 | 0.9006 | 0.8870 | 0.8464 |
61
- | 0.3785 | 25.0 | 750 | 0.8247 | 0.8904 | 0.9081 | 0.8992 | 0.8395 |
62
- | 0.0358 | 33.3333 | 1000 | 0.9665 | 0.9099 | 0.9131 | 0.9115 | 0.8480 |
63
- | 0.0358 | 41.6667 | 1250 | 0.9769 | 0.9012 | 0.9016 | 0.9014 | 0.8556 |
64
- | 0.0079 | 50.0 | 1500 | 1.0142 | 0.9000 | 0.9071 | 0.9035 | 0.8527 |
65
- | 0.0079 | 58.3333 | 1750 | 1.1102 | 0.9018 | 0.9076 | 0.9047 | 0.8499 |
66
- | 0.0021 | 66.6667 | 2000 | 1.1022 | 0.9019 | 0.8997 | 0.9008 | 0.8572 |
67
- | 0.0021 | 75.0 | 2250 | 1.1009 | 0.9017 | 0.9111 | 0.9064 | 0.8547 |
68
- | 0.0013 | 83.3333 | 2500 | 1.1047 | 0.9013 | 0.9076 | 0.9045 | 0.8536 |
69
 
70
 
71
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.8423
25
+ - Precision: 0.8933
26
+ - Recall: 0.9091
27
+ - F1: 0.9011
28
+ - Accuracy: 0.7616
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 1e-05
48
+ - train_batch_size: 4
49
+ - eval_batch_size: 4
50
  - seed: 42
51
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
+ - training_steps: 1000
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 16.6667 | 250 | 1.1352 | 0.8427 | 0.8760 | 0.8590 | 0.7717 |
60
+ | 0.2698 | 33.3333 | 500 | 1.5871 | 0.8825 | 0.9044 | 0.8933 | 0.7534 |
61
+ | 0.2698 | 50.0 | 750 | 1.8174 | 0.8891 | 0.9038 | 0.8964 | 0.7551 |
62
+ | 0.0057 | 66.6667 | 1000 | 1.8423 | 0.8933 | 0.9091 | 0.9011 | 0.7616 |
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6485572ef0f42da75bdfd41588bbe8a4f9784e232fd33cdd3a8827f7fac08dc
3
  size 501355532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065f84399f1483c7fa7da552c8014e86540fbd430188d95304b02fc5fa3f6c9a
3
  size 501355532
runs/Jan02_09-56-45_117a15486a19/events.out.tfevents.1735811814.117a15486a19.1160.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71688bdbfa8990e17576ebcf2149d508884a8fe2505b5b09cf9a9763d83c89af
3
+ size 8403
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f83f4e16b3d6402c95e96440018e46ef6eb0b9275a7ebbcae4e4b0c1dc697b3
3
- size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85cca340219a7bf312e44cb9cac1a118c1019cb9d0020c56fe7893f8144f53b
3
+ size 5368