Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: bert-base-multilingual-cased
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- tmnam20/VieGLUE
|
10 |
+
metrics:
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: bert-base-multilingual-cased-sst2-10
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: tmnam20/VieGLUE/SST2
|
20 |
+
type: tmnam20/VieGLUE
|
21 |
+
config: sst2
|
22 |
+
split: validation
|
23 |
+
args: sst2
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.8841743119266054
|
28 |
+
---
|
29 |
+
|
30 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
31 |
+
should probably proofread and complete it, then remove this comment. -->
|
32 |
+
|
33 |
+
# bert-base-multilingual-cased-sst2-10
|
34 |
+
|
35 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/SST2 dataset.
|
36 |
+
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.4234
|
38 |
+
- Accuracy: 0.8842
|
39 |
+
|
40 |
+
## Model description
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Intended uses & limitations
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training and evaluation data
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Training procedure
|
53 |
+
|
54 |
+
### Training hyperparameters
|
55 |
+
|
56 |
+
The following hyperparameters were used during training:
|
57 |
+
- learning_rate: 2e-05
|
58 |
+
- train_batch_size: 32
|
59 |
+
- eval_batch_size: 16
|
60 |
+
- seed: 10
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- num_epochs: 3.0
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
+
| 0.4066 | 0.24 | 500 | 0.3869 | 0.8291 |
|
70 |
+
| 0.3414 | 0.48 | 1000 | 0.3499 | 0.8486 |
|
71 |
+
| 0.3133 | 0.71 | 1500 | 0.3743 | 0.8509 |
|
72 |
+
| 0.2797 | 0.95 | 2000 | 0.4119 | 0.8475 |
|
73 |
+
| 0.236 | 1.19 | 2500 | 0.3891 | 0.8670 |
|
74 |
+
| 0.2202 | 1.43 | 3000 | 0.3640 | 0.8739 |
|
75 |
+
| 0.1889 | 1.66 | 3500 | 0.3829 | 0.8681 |
|
76 |
+
| 0.1847 | 1.9 | 4000 | 0.3687 | 0.8796 |
|
77 |
+
| 0.1288 | 2.14 | 4500 | 0.4524 | 0.8807 |
|
78 |
+
| 0.1478 | 2.38 | 5000 | 0.4259 | 0.875 |
|
79 |
+
| 0.1761 | 2.61 | 5500 | 0.4060 | 0.8819 |
|
80 |
+
| 0.1487 | 2.85 | 6000 | 0.4408 | 0.8807 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.35.2
|
86 |
+
- Pytorch 2.2.0.dev20231203+cu121
|
87 |
+
- Datasets 2.15.0
|
88 |
+
- Tokenizers 0.15.0
|