Model save
Browse files- README.md +89 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: ys7yoo/sts_roberta_large_lr1e-05_wd1e-03_ep10
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- klue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: nli_sts_roberta_large_lr1e-05_wd1e-03_ep10_lr1e-05_wd1e-03_ep10_ckpt
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: klue
|
18 |
+
type: klue
|
19 |
+
config: nli
|
20 |
+
split: validation
|
21 |
+
args: nli
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8963333333333333
|
26 |
+
- name: F1
|
27 |
+
type: f1
|
28 |
+
value: 0.8962457758881018
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# nli_sts_roberta_large_lr1e-05_wd1e-03_ep10_lr1e-05_wd1e-03_ep10_ckpt
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [ys7yoo/sts_roberta_large_lr1e-05_wd1e-03_ep10](https://huggingface.co/ys7yoo/sts_roberta_large_lr1e-05_wd1e-03_ep10) on the klue dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.6903
|
39 |
+
- Accuracy: 0.8963
|
40 |
+
- F1: 0.8962
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 1e-05
|
60 |
+
- train_batch_size: 64
|
61 |
+
- eval_batch_size: 64
|
62 |
+
- seed: 42
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- lr_scheduler_warmup_ratio: 0.1
|
66 |
+
- num_epochs: 10
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
72 |
+
| 0.6445 | 1.0 | 391 | 0.4254 | 0.852 | 0.8512 |
|
73 |
+
| 0.2943 | 2.0 | 782 | 0.3371 | 0.889 | 0.8886 |
|
74 |
+
| 0.1586 | 3.0 | 1173 | 0.3704 | 0.888 | 0.8881 |
|
75 |
+
| 0.0921 | 4.0 | 1564 | 0.4429 | 0.892 | 0.8919 |
|
76 |
+
| 0.0565 | 5.0 | 1955 | 0.4864 | 0.899 | 0.8989 |
|
77 |
+
| 0.0378 | 6.0 | 2346 | 0.5727 | 0.8963 | 0.8962 |
|
78 |
+
| 0.0238 | 7.0 | 2737 | 0.6247 | 0.8957 | 0.8955 |
|
79 |
+
| 0.016 | 8.0 | 3128 | 0.6578 | 0.8947 | 0.8945 |
|
80 |
+
| 0.0101 | 9.0 | 3519 | 0.6780 | 0.8953 | 0.8952 |
|
81 |
+
| 0.0067 | 10.0 | 3910 | 0.6903 | 0.8963 | 0.8962 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.33.2
|
87 |
+
- Pytorch 2.0.1+cu117
|
88 |
+
- Datasets 2.13.0
|
89 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1346773425
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0989ccdbdfce24d4d7c27b210b4bcb3a62e85072001e6e352b7163b4a5fc6c
|
3 |
size 1346773425
|