Instructions to use Matt6450/layoutlm-funsd-tf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Matt6450/layoutlm-funsd-tf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Matt6450/layoutlm-funsd-tf")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Matt6450/layoutlm-funsd-tf") model = AutoModelForTokenClassification.from_pretrained("Matt6450/layoutlm-funsd-tf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress epoch 0
Browse files
README.md
CHANGED
|
@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 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:
|
| 19 |
-
- Validation Loss: 1.
|
| 20 |
-
- Train Overall Precision: 0.
|
| 21 |
-
- Train Overall Recall: 0.
|
| 22 |
-
- Train Overall F1: 0.
|
| 23 |
-
- Train Overall Accuracy: 0.
|
| 24 |
-
- Epoch:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -47,27 +47,7 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|
| 49 |
|:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
|
| 50 |
-
| 1.
|
| 51 |
-
| 1.4242 | 1.2830 | 0.2487 | 0.4175 | 0.3117 | 0.4566 | 1 |
|
| 52 |
-
| 1.2526 | 1.1590 | 0.3177 | 0.4516 | 0.3730 | 0.5549 | 2 |
|
| 53 |
-
| 1.1361 | 1.0902 | 0.3488 | 0.4852 | 0.4059 | 0.5809 | 3 |
|
| 54 |
-
| 1.0227 | 1.1117 | 0.3790 | 0.5359 | 0.4440 | 0.5767 | 4 |
|
| 55 |
-
| 0.9273 | 0.9989 | 0.4099 | 0.5389 | 0.4656 | 0.6186 | 5 |
|
| 56 |
-
| 0.8036 | 1.0160 | 0.4273 | 0.5620 | 0.4855 | 0.6180 | 6 |
|
| 57 |
-
| 0.7326 | 1.0012 | 0.4625 | 0.5534 | 0.5039 | 0.6312 | 7 |
|
| 58 |
-
| 0.6494 | 1.0685 | 0.4365 | 0.5635 | 0.4919 | 0.6286 | 8 |
|
| 59 |
-
| 0.5981 | 1.0667 | 0.4332 | 0.5615 | 0.4891 | 0.6312 | 9 |
|
| 60 |
-
| 0.5377 | 1.1656 | 0.5009 | 0.5504 | 0.5245 | 0.6332 | 10 |
|
| 61 |
-
| 0.5181 | 1.3655 | 0.4409 | 0.5936 | 0.5060 | 0.5940 | 11 |
|
| 62 |
-
| 0.4712 | 1.0981 | 0.4619 | 0.5745 | 0.5121 | 0.6373 | 12 |
|
| 63 |
-
| 0.4138 | 1.1086 | 0.4859 | 0.5695 | 0.5244 | 0.6228 | 13 |
|
| 64 |
-
| 0.3699 | 1.1288 | 0.4974 | 0.5815 | 0.5362 | 0.6347 | 14 |
|
| 65 |
-
| 0.3384 | 1.1199 | 0.5114 | 0.5876 | 0.5468 | 0.6401 | 15 |
|
| 66 |
-
| 0.3097 | 1.4032 | 0.4921 | 0.5966 | 0.5394 | 0.6157 | 16 |
|
| 67 |
-
| 0.2716 | 1.1890 | 0.5134 | 0.5850 | 0.5469 | 0.6536 | 17 |
|
| 68 |
-
| 0.2638 | 1.3274 | 0.5024 | 0.5795 | 0.5382 | 0.6306 | 18 |
|
| 69 |
-
| 0.2266 | 1.3596 | 0.5149 | 0.5800 | 0.5455 | 0.6395 | 19 |
|
| 70 |
-
| 0.2354 | 1.2861 | 0.5106 | 0.5911 | 0.5479 | 0.6490 | 20 |
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
|
|
|
| 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: 1.7401
|
| 19 |
+
- Validation Loss: 1.5464
|
| 20 |
+
- Train Overall Precision: 0.0930
|
| 21 |
+
- Train Overall Recall: 0.1174
|
| 22 |
+
- Train Overall F1: 0.1038
|
| 23 |
+
- Train Overall Accuracy: 0.3843
|
| 24 |
+
- Epoch: 0
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 47 |
|
| 48 |
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|
| 49 |
|:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
|
| 50 |
+
| 1.7401 | 1.5464 | 0.0930 | 0.1174 | 0.1038 | 0.3843 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
logs/train/events.out.tfevents.1708326890.c65eaeed6165.295.0.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:968753c589402d0f2a11fc209e3fe04eb8c89f41e0a69c48690a96c9bdb303e3
|
| 3 |
+
size 2364935
|
logs/validation/events.out.tfevents.1708326925.c65eaeed6165.295.1.v2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d3a2586e7114eb284faa77a43885ff8a7f42f214011d03e38045a1dbcc6d34
|
| 3 |
+
size 231
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 450829256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b52c5ac9a924c359545b7687e0ba3ad5251a5a25702b7ae21dd455c835c25131
|
| 3 |
size 450829256
|