update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- mn
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: mongolian-roberta-base
|
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 |
+
# mongolian-roberta-base
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1308
|
24 |
+
- Precision: 0.9243
|
25 |
+
- Recall: 0.9322
|
26 |
+
- F1: 0.9283
|
27 |
+
- Accuracy: 0.9799
|
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: 16
|
48 |
+
- eval_batch_size: 32
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 9
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.1632 | 1.0 | 477 | 0.0908 | 0.8293 | 0.8817 | 0.8547 | 0.9682 |
|
59 |
+
| 0.0607 | 2.0 | 954 | 0.0920 | 0.8506 | 0.8898 | 0.8698 | 0.9712 |
|
60 |
+
| 0.0331 | 3.0 | 1431 | 0.0975 | 0.9192 | 0.9267 | 0.9229 | 0.9779 |
|
61 |
+
| 0.0148 | 4.0 | 1908 | 0.1024 | 0.9179 | 0.9294 | 0.9236 | 0.9786 |
|
62 |
+
| 0.0087 | 5.0 | 2385 | 0.1091 | 0.9196 | 0.9296 | 0.9246 | 0.9796 |
|
63 |
+
| 0.0052 | 6.0 | 2862 | 0.1222 | 0.9240 | 0.9323 | 0.9281 | 0.9794 |
|
64 |
+
| 0.0033 | 7.0 | 3339 | 0.1233 | 0.9214 | 0.9317 | 0.9265 | 0.9796 |
|
65 |
+
| 0.0024 | 8.0 | 3816 | 0.1310 | 0.9250 | 0.9315 | 0.9282 | 0.9797 |
|
66 |
+
| 0.0016 | 9.0 | 4293 | 0.1308 | 0.9243 | 0.9322 | 0.9283 | 0.9799 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.28.0
|
72 |
+
- Pytorch 2.0.1+cu118
|
73 |
+
- Datasets 2.12.0
|
74 |
+
- Tokenizers 0.13.3
|