update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: distilbert-base-uncased-ner-invoiceSenderRecipient_clean_inv_27_02
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# distilbert-base-uncased-ner-invoiceSenderRecipient_clean_inv_27_02
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0160
|
| 23 |
+
- Precision: 0.9514
|
| 24 |
+
- Recall: 0.9593
|
| 25 |
+
- F1: 0.9553
|
| 26 |
+
- Accuracy: 0.9953
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 2e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 16
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 2
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.0078 | 0.09 | 500 | 0.0213 | 0.9269 | 0.9514 | 0.9390 | 0.9937 |
|
| 59 |
+
| 0.008 | 0.17 | 1000 | 0.0230 | 0.9246 | 0.9516 | 0.9379 | 0.9935 |
|
| 60 |
+
| 0.007 | 0.26 | 1500 | 0.0234 | 0.9400 | 0.9478 | 0.9439 | 0.9942 |
|
| 61 |
+
| 0.0065 | 0.34 | 2000 | 0.0238 | 0.9280 | 0.9537 | 0.9406 | 0.9936 |
|
| 62 |
+
| 0.0071 | 0.43 | 2500 | 0.0221 | 0.9291 | 0.9570 | 0.9428 | 0.9939 |
|
| 63 |
+
| 0.007 | 0.52 | 3000 | 0.0210 | 0.9393 | 0.9457 | 0.9425 | 0.9941 |
|
| 64 |
+
| 0.0072 | 0.6 | 3500 | 0.0197 | 0.9448 | 0.9490 | 0.9469 | 0.9945 |
|
| 65 |
+
| 0.0071 | 0.69 | 4000 | 0.0196 | 0.9400 | 0.9555 | 0.9477 | 0.9945 |
|
| 66 |
+
| 0.0109 | 0.77 | 4500 | 0.0178 | 0.9458 | 0.9499 | 0.9478 | 0.9946 |
|
| 67 |
+
| 0.01 | 0.86 | 5000 | 0.0191 | 0.9443 | 0.9489 | 0.9466 | 0.9945 |
|
| 68 |
+
| 0.0103 | 0.95 | 5500 | 0.0181 | 0.9466 | 0.9530 | 0.9498 | 0.9947 |
|
| 69 |
+
| 0.0081 | 1.03 | 6000 | 0.0191 | 0.9448 | 0.9578 | 0.9512 | 0.9948 |
|
| 70 |
+
| 0.0102 | 1.12 | 6500 | 0.0171 | 0.9454 | 0.9550 | 0.9502 | 0.9948 |
|
| 71 |
+
| 0.01 | 1.21 | 7000 | 0.0178 | 0.9460 | 0.9584 | 0.9521 | 0.9949 |
|
| 72 |
+
| 0.0107 | 1.29 | 7500 | 0.0164 | 0.9498 | 0.9552 | 0.9525 | 0.9950 |
|
| 73 |
+
| 0.0107 | 1.38 | 8000 | 0.0166 | 0.9461 | 0.9596 | 0.9528 | 0.9950 |
|
| 74 |
+
| 0.0095 | 1.46 | 8500 | 0.0170 | 0.9402 | 0.9626 | 0.9513 | 0.9949 |
|
| 75 |
+
| 0.0097 | 1.55 | 9000 | 0.0161 | 0.9455 | 0.9595 | 0.9524 | 0.9950 |
|
| 76 |
+
| 0.01 | 1.64 | 9500 | 0.0159 | 0.9502 | 0.9583 | 0.9542 | 0.9952 |
|
| 77 |
+
| 0.01 | 1.72 | 10000 | 0.0160 | 0.9488 | 0.9598 | 0.9543 | 0.9952 |
|
| 78 |
+
| 0.0095 | 1.81 | 10500 | 0.0157 | 0.9502 | 0.9602 | 0.9552 | 0.9953 |
|
| 79 |
+
| 0.0087 | 1.89 | 11000 | 0.0160 | 0.9514 | 0.9593 | 0.9553 | 0.9953 |
|
| 80 |
+
| 0.0089 | 1.98 | 11500 | 0.0160 | 0.9502 | 0.9608 | 0.9555 | 0.9953 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.15.0
|
| 86 |
+
- Pytorch 1.13.1
|
| 87 |
+
- Datasets 2.3.2
|
| 88 |
+
- Tokenizers 0.10.3
|