Commit
•
58bf6d6
1
Parent(s):
00a1f58
Model save
Browse files- README.md +94 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- super_glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: superglue_rte-t5-base
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: super_glue
|
18 |
+
type: super_glue
|
19 |
+
config: rte
|
20 |
+
split: validation
|
21 |
+
args: rte
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.7725631768953068
|
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 |
+
# superglue_rte-t5-base
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the super_glue dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.5687
|
36 |
+
- Accuracy: 0.7726
|
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: 5e-05
|
56 |
+
- train_batch_size: 4
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 20
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
67 |
+
| 0.7109 | 1.0 | 623 | 0.6765 | 0.5740 |
|
68 |
+
| 0.6562 | 2.0 | 1246 | 0.6030 | 0.6968 |
|
69 |
+
| 0.548 | 3.0 | 1869 | 0.8049 | 0.7617 |
|
70 |
+
| 0.4129 | 4.0 | 2492 | 1.3536 | 0.7329 |
|
71 |
+
| 0.2189 | 5.0 | 3115 | 1.3886 | 0.7834 |
|
72 |
+
| 0.1378 | 6.0 | 3738 | 1.7001 | 0.7690 |
|
73 |
+
| 0.0905 | 7.0 | 4361 | 2.0587 | 0.7545 |
|
74 |
+
| 0.0434 | 8.0 | 4984 | 2.1796 | 0.7798 |
|
75 |
+
| 0.0715 | 9.0 | 5607 | 1.9936 | 0.7978 |
|
76 |
+
| 0.0616 | 10.0 | 6230 | 1.9794 | 0.7762 |
|
77 |
+
| 0.0609 | 11.0 | 6853 | 2.5575 | 0.7509 |
|
78 |
+
| 0.0108 | 12.0 | 7476 | 2.1022 | 0.7834 |
|
79 |
+
| 0.0142 | 13.0 | 8099 | 2.0628 | 0.7834 |
|
80 |
+
| 0.03 | 14.0 | 8722 | 2.1540 | 0.7726 |
|
81 |
+
| 0.0163 | 15.0 | 9345 | 2.3830 | 0.7653 |
|
82 |
+
| 0.0152 | 16.0 | 9968 | 2.5031 | 0.7617 |
|
83 |
+
| 0.0092 | 17.0 | 10591 | 2.4850 | 0.7653 |
|
84 |
+
| 0.0069 | 18.0 | 11214 | 2.4939 | 0.7726 |
|
85 |
+
| 0.0184 | 19.0 | 11837 | 2.4949 | 0.7690 |
|
86 |
+
| 0.0204 | 20.0 | 12460 | 2.5687 | 0.7726 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.32.1
|
92 |
+
- Pytorch 1.13.0+cu117
|
93 |
+
- Datasets 2.15.0
|
94 |
+
- 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 894075745
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeec426ce24f44ab6830772e8621c9466046ae2222256b06092de3fdd3770ed9
|
3 |
size 894075745
|