Commit
•
eec1cb3
1
Parent(s):
5fde1d7
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: kennethge123/superglue_rte-t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- bigbench
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: entailed_after_rte-t5-base
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: bigbench
|
18 |
+
type: bigbench
|
19 |
+
config: entailed_polarity
|
20 |
+
split: validation
|
21 |
+
args: entailed_polarity
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 1.0
|
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 |
+
# entailed_after_rte-t5-base
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [kennethge123/superglue_rte-t5-base](https://huggingface.co/kennethge123/superglue_rte-t5-base) on the bigbench dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0000
|
36 |
+
- Accuracy: 1.0
|
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 |
+
| No log | 1.0 | 30 | 0.7892 | 0.5714 |
|
68 |
+
| No log | 2.0 | 60 | 1.0497 | 0.7143 |
|
69 |
+
| No log | 3.0 | 90 | 1.5272 | 0.7857 |
|
70 |
+
| No log | 4.0 | 120 | 0.0498 | 1.0 |
|
71 |
+
| No log | 5.0 | 150 | 0.0000 | 1.0 |
|
72 |
+
| No log | 6.0 | 180 | 0.0000 | 1.0 |
|
73 |
+
| No log | 7.0 | 210 | 0.0000 | 1.0 |
|
74 |
+
| No log | 8.0 | 240 | 0.0000 | 1.0 |
|
75 |
+
| No log | 9.0 | 270 | 0.0000 | 1.0 |
|
76 |
+
| No log | 10.0 | 300 | 0.0000 | 1.0 |
|
77 |
+
| No log | 11.0 | 330 | 0.0000 | 1.0 |
|
78 |
+
| No log | 12.0 | 360 | 0.0000 | 1.0 |
|
79 |
+
| No log | 13.0 | 390 | 0.0000 | 1.0 |
|
80 |
+
| No log | 14.0 | 420 | 0.0000 | 1.0 |
|
81 |
+
| No log | 15.0 | 450 | 0.0000 | 1.0 |
|
82 |
+
| No log | 16.0 | 480 | 0.0000 | 1.0 |
|
83 |
+
| 0.1757 | 17.0 | 510 | 0.0000 | 1.0 |
|
84 |
+
| 0.1757 | 18.0 | 540 | 0.0000 | 1.0 |
|
85 |
+
| 0.1757 | 19.0 | 570 | 0.0000 | 1.0 |
|
86 |
+
| 0.1757 | 20.0 | 600 | 0.0000 | 1.0 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.37.0
|
92 |
+
- Pytorch 1.13.1+cu117
|
93 |
+
- Datasets 2.15.0
|
94 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 894016712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c829799f573a551e63b80923467adc36e21f7f4658515fbb1f1cfdc1f917b25b
|
3 |
size 894016712
|
runs/Mar27_00-08-32_dsail2/events.out.tfevents.1711512513.dsail2.23957.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3df09e079e89204f94496fc8633c9647cf7c61d39c44e4cf560a5bc7cb3287a
|
3 |
+
size 12271
|