NER Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: roberta-lg-cased-ms-ner-v3-test
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# roberta-lg-cased-ms-ner-v3-test
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1071
|
24 |
+
- Precision: 0.8912
|
25 |
+
- Recall: 0.9039
|
26 |
+
- F1: 0.8975
|
27 |
+
- Accuracy: 0.9813
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.1478 | 1.0 | 3615 | 0.1187 | 0.8247 | 0.8225 | 0.8236 | 0.9687 |
|
59 |
+
| 0.0909 | 2.0 | 7230 | 0.1025 | 0.8617 | 0.8702 | 0.8659 | 0.9753 |
|
60 |
+
| 0.0552 | 3.0 | 10845 | 0.1016 | 0.8789 | 0.8886 | 0.8837 | 0.9790 |
|
61 |
+
| 0.0325 | 4.0 | 14460 | 0.0966 | 0.8958 | 0.8956 | 0.8957 | 0.9815 |
|
62 |
+
| 0.0185 | 5.0 | 18075 | 0.1071 | 0.8912 | 0.9039 | 0.8975 | 0.9813 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.39.3
|
68 |
+
- Pytorch 1.12.0
|
69 |
+
- Datasets 2.18.0
|
70 |
+
- Tokenizers 0.15.2
|