Commit
•
114f307
1
Parent(s):
fc009b5
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: retrained_ner
|
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 |
+
# retrained_ner
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0829
|
23 |
+
- Precision: 0.9435
|
24 |
+
- Recall: 0.9497
|
25 |
+
- F1: 0.9466
|
26 |
+
- Accuracy: 0.9868
|
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: 5e-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: 10
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.1292 | 1.0 | 878 | 0.0580 | 0.9201 | 0.9355 | 0.9277 | 0.9836 |
|
59 |
+
| 0.0394 | 2.0 | 1756 | 0.0613 | 0.9283 | 0.9415 | 0.9349 | 0.9847 |
|
60 |
+
| 0.0207 | 3.0 | 2634 | 0.0635 | 0.9398 | 0.9490 | 0.9444 | 0.9865 |
|
61 |
+
| 0.0117 | 4.0 | 3512 | 0.0688 | 0.9363 | 0.9455 | 0.9409 | 0.9857 |
|
62 |
+
| 0.0074 | 5.0 | 4390 | 0.0691 | 0.9416 | 0.9480 | 0.9448 | 0.9864 |
|
63 |
+
| 0.0043 | 6.0 | 5268 | 0.0803 | 0.9356 | 0.9466 | 0.9411 | 0.9861 |
|
64 |
+
| 0.0035 | 7.0 | 6146 | 0.0801 | 0.9435 | 0.9508 | 0.9471 | 0.9870 |
|
65 |
+
| 0.0021 | 8.0 | 7024 | 0.0825 | 0.9394 | 0.9491 | 0.9442 | 0.9860 |
|
66 |
+
| 0.0015 | 9.0 | 7902 | 0.0800 | 0.9421 | 0.9489 | 0.9455 | 0.9865 |
|
67 |
+
| 0.001 | 10.0 | 8780 | 0.0829 | 0.9435 | 0.9497 | 0.9466 | 0.9868 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.28.0
|
73 |
+
- Pytorch 2.2.1+cu121
|
74 |
+
- Datasets 2.19.0
|
75 |
+
- Tokenizers 0.13.3
|