update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: deberta-v3-large__sst2__train-8-2
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# deberta-v3-large__sst2__train-8-2
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.6794
|
20 |
+
- Accuracy: 0.6063
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 50
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 0.6942 | 1.0 | 3 | 0.7940 | 0.25 |
|
53 |
+
| 0.6068 | 2.0 | 6 | 0.9326 | 0.25 |
|
54 |
+
| 0.6553 | 3.0 | 9 | 0.7979 | 0.25 |
|
55 |
+
| 0.475 | 4.0 | 12 | 0.7775 | 0.25 |
|
56 |
+
| 0.377 | 5.0 | 15 | 0.7477 | 0.25 |
|
57 |
+
| 0.3176 | 6.0 | 18 | 0.6856 | 0.75 |
|
58 |
+
| 0.2708 | 7.0 | 21 | 0.6554 | 0.75 |
|
59 |
+
| 0.2855 | 8.0 | 24 | 0.8129 | 0.5 |
|
60 |
+
| 0.148 | 9.0 | 27 | 0.7074 | 0.75 |
|
61 |
+
| 0.0947 | 10.0 | 30 | 0.7090 | 0.75 |
|
62 |
+
| 0.049 | 11.0 | 33 | 0.7885 | 0.75 |
|
63 |
+
| 0.0252 | 12.0 | 36 | 0.9203 | 0.75 |
|
64 |
+
| 0.0165 | 13.0 | 39 | 1.0937 | 0.75 |
|
65 |
+
| 0.0084 | 14.0 | 42 | 1.2502 | 0.75 |
|
66 |
+
| 0.0059 | 15.0 | 45 | 1.3726 | 0.75 |
|
67 |
+
| 0.0037 | 16.0 | 48 | 1.4784 | 0.75 |
|
68 |
+
| 0.003 | 17.0 | 51 | 1.5615 | 0.75 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.15.0
|
74 |
+
- Pytorch 1.10.2+cu102
|
75 |
+
- Datasets 1.18.2
|
76 |
+
- Tokenizers 0.10.3
|