axljeremy7
commited on
Commit
•
5787b78
1
Parent(s):
391ee01
Model save
Browse files- .DS_Store +0 -0
- README.md +89 -0
- model.safetensors +1 -1
.DS_Store
CHANGED
Binary files a/.DS_Store and b/.DS_Store differ
|
|
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: bert-base-uncased-finetuned-CLS-RTE
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: glue
|
18 |
+
type: glue
|
19 |
+
config: rte
|
20 |
+
split: validation
|
21 |
+
args: rte
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.6967509025270758
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# bert-base-uncased-finetuned-CLS-RTE
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.2843
|
36 |
+
- Accuracy: 0.6968
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 2e-05
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 15
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| No log | 1.0 | 156 | 0.6285 | 0.6390 |
|
68 |
+
| No log | 2.0 | 312 | 0.6483 | 0.6679 |
|
69 |
+
| No log | 3.0 | 468 | 0.8430 | 0.7004 |
|
70 |
+
| 0.4504 | 4.0 | 624 | 1.2886 | 0.6606 |
|
71 |
+
| 0.4504 | 5.0 | 780 | 1.6445 | 0.7004 |
|
72 |
+
| 0.4504 | 6.0 | 936 | 1.8099 | 0.6751 |
|
73 |
+
| 0.0631 | 7.0 | 1092 | 1.8173 | 0.7040 |
|
74 |
+
| 0.0631 | 8.0 | 1248 | 1.9799 | 0.7004 |
|
75 |
+
| 0.0631 | 9.0 | 1404 | 1.9767 | 0.6968 |
|
76 |
+
| 0.0159 | 10.0 | 1560 | 2.1696 | 0.6715 |
|
77 |
+
| 0.0159 | 11.0 | 1716 | 2.2142 | 0.6859 |
|
78 |
+
| 0.0159 | 12.0 | 1872 | 2.2605 | 0.6823 |
|
79 |
+
| 0.0076 | 13.0 | 2028 | 2.2775 | 0.7040 |
|
80 |
+
| 0.0076 | 14.0 | 2184 | 2.2719 | 0.6968 |
|
81 |
+
| 0.0076 | 15.0 | 2340 | 2.2843 | 0.6968 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.36.1
|
87 |
+
- Pytorch 2.1.2
|
88 |
+
- Datasets 2.15.0
|
89 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adaf6a97fe17e1f2bfd04149f5b1a7a1c78115e16cd66f4cc1009612f4857936
|
3 |
size 437958648
|