Commit
•
a8dd423
1
Parent(s):
1969e61
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- text-classification
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: deberta-v3-large-dapt-scientific-papers-pubmed-finetuned-DAGPap22
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# deberta-v3-large-dapt-scientific-papers-pubmed-finetuned-DAGPap22
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [domenicrosati/deberta-v3-large-dapt-scientific-papers-pubmed](https://huggingface.co/domenicrosati/deberta-v3-large-dapt-scientific-papers-pubmed) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0000
|
22 |
+
- Accuracy: 1.0
|
23 |
+
- F1: 1.0
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 6e-06
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 50
|
49 |
+
- num_epochs: 12
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
56 |
+
| 0.2165 | 1.0 | 669 | 0.0218 | 0.9963 | 0.9973 |
|
57 |
+
| 0.0717 | 2.0 | 1338 | 0.0213 | 0.9964 | 0.9974 |
|
58 |
+
| 0.03 | 3.0 | 2007 | 0.0121 | 0.9983 | 0.9988 |
|
59 |
+
| 0.0165 | 4.0 | 2676 | 0.0147 | 0.9976 | 0.9982 |
|
60 |
+
| 0.0072 | 5.0 | 3345 | 0.0000 | 1.0 | 1.0 |
|
61 |
+
| 0.0055 | 6.0 | 4014 | 0.0000 | 1.0 | 1.0 |
|
62 |
+
| 0.0077 | 7.0 | 4683 | 0.0000 | 1.0 | 1.0 |
|
63 |
+
| 0.0 | 8.0 | 5352 | 0.0000 | 1.0 | 1.0 |
|
64 |
+
| 0.0 | 9.0 | 6021 | 0.0000 | 1.0 | 1.0 |
|
65 |
+
| 0.0 | 10.0 | 6690 | 0.0000 | 1.0 | 1.0 |
|
66 |
+
| 0.0 | 11.0 | 7359 | 0.0000 | 1.0 | 1.0 |
|
67 |
+
| 0.0 | 12.0 | 8028 | 0.0000 | 1.0 | 1.0 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.18.0
|
73 |
+
- Pytorch 1.11.0
|
74 |
+
- Datasets 2.1.0
|
75 |
+
- Tokenizers 0.12.1
|