commanderstrife
commited on
Commit
•
ac587c2
1
Parent(s):
710df35
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: distilBERT_bio_pv_superset
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# distilBERT_bio_pv_superset
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.2328
|
23 |
+
- Precision: 0.5462
|
24 |
+
- Recall: 0.5325
|
25 |
+
- F1: 0.5393
|
26 |
+
- Accuracy: 0.9495
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 2e-05
|
46 |
+
- train_batch_size: 16
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 0.0964 | 1.0 | 5467 | 0.1593 | 0.4625 | 0.3682 | 0.4100 | 0.9416 |
|
58 |
+
| 0.1918 | 2.0 | 10934 | 0.1541 | 0.4796 | 0.4658 | 0.4726 | 0.9436 |
|
59 |
+
| 0.0394 | 3.0 | 16401 | 0.1508 | 0.5349 | 0.4744 | 0.5028 | 0.9482 |
|
60 |
+
| 0.1207 | 4.0 | 21868 | 0.1615 | 0.5422 | 0.4953 | 0.5177 | 0.9490 |
|
61 |
+
| 0.0221 | 5.0 | 27335 | 0.1827 | 0.5377 | 0.5018 | 0.5191 | 0.9487 |
|
62 |
+
| 0.0629 | 6.0 | 32802 | 0.1874 | 0.5479 | 0.5130 | 0.5299 | 0.9493 |
|
63 |
+
| 0.0173 | 7.0 | 38269 | 0.2025 | 0.5388 | 0.5323 | 0.5356 | 0.9488 |
|
64 |
+
| 0.2603 | 8.0 | 43736 | 0.2148 | 0.5437 | 0.5397 | 0.5417 | 0.9493 |
|
65 |
+
| 0.0378 | 9.0 | 49203 | 0.2323 | 0.5430 | 0.5194 | 0.5310 | 0.9489 |
|
66 |
+
| 0.031 | 10.0 | 54670 | 0.2328 | 0.5462 | 0.5325 | 0.5393 | 0.9495 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.21.0
|
72 |
+
- Pytorch 1.12.0+cu113
|
73 |
+
- Datasets 2.4.0
|
74 |
+
- Tokenizers 0.12.1
|