Baljinnyam
commited on
Commit
•
faed1b9
1
Parent(s):
085477c
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- mn
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: bloom-mongolian-ner-demo
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# bloom-mongolian-ner-demo
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.1048
|
25 |
+
- Precision: 0.9267
|
26 |
+
- Recall: 0.9354
|
27 |
+
- F1: 0.9310
|
28 |
+
- Accuracy: 0.9796
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 2e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 32
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 10
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 0.195 | 1.0 | 477 | 0.0947 | 0.8845 | 0.8994 | 0.8919 | 0.9707 |
|
60 |
+
| 0.0848 | 2.0 | 954 | 0.0761 | 0.9095 | 0.9235 | 0.9164 | 0.9774 |
|
61 |
+
| 0.0614 | 3.0 | 1431 | 0.0724 | 0.9218 | 0.9317 | 0.9267 | 0.9797 |
|
62 |
+
| 0.0452 | 4.0 | 1908 | 0.0756 | 0.9283 | 0.9350 | 0.9316 | 0.9806 |
|
63 |
+
| 0.035 | 5.0 | 2385 | 0.0824 | 0.9221 | 0.9337 | 0.9279 | 0.9796 |
|
64 |
+
| 0.0263 | 6.0 | 2862 | 0.0895 | 0.9191 | 0.9319 | 0.9254 | 0.9787 |
|
65 |
+
| 0.02 | 7.0 | 3339 | 0.0991 | 0.9238 | 0.9335 | 0.9286 | 0.9789 |
|
66 |
+
| 0.0148 | 8.0 | 3816 | 0.1005 | 0.9277 | 0.9358 | 0.9317 | 0.9798 |
|
67 |
+
| 0.0124 | 9.0 | 4293 | 0.1014 | 0.9254 | 0.9356 | 0.9305 | 0.9801 |
|
68 |
+
| 0.01 | 10.0 | 4770 | 0.1048 | 0.9267 | 0.9354 | 0.9310 | 0.9796 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.27.4
|
74 |
+
- Pytorch 2.0.0+cu118
|
75 |
+
- Datasets 2.11.0
|
76 |
+
- Tokenizers 0.13.3
|