update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: protBERTbfd_AAV2_regressor
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# protBERTbfd_AAV2_regressor
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [Rostlab/prot_bert_bfd](https://huggingface.co/Rostlab/prot_bert_bfd) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.0327
|
17 |
+
- Mse: 0.0327
|
18 |
+
- Rmse: 0.1808
|
19 |
+
- Mae: 0.0618
|
20 |
+
- R2: 0.8691
|
21 |
+
- Smape: 101.2324
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 64
|
42 |
+
- eval_batch_size: 64
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 64
|
45 |
+
- total_train_batch_size: 4096
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 200
|
49 |
+
- num_epochs: 6
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Mse | Rmse | Mae | R2 | Smape |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|:--------:|
|
55 |
+
| No log | 1.0 | 58 | 0.0985 | 0.0985 | 0.3138 | 0.1707 | 0.6057 | 102.5806 |
|
56 |
+
| No log | 2.0 | 116 | 0.0689 | 0.0689 | 0.2625 | 0.1432 | 0.7242 | 112.9846 |
|
57 |
+
| No log | 3.0 | 174 | 0.0400 | 0.0400 | 0.1999 | 0.0859 | 0.8399 | 102.6132 |
|
58 |
+
| No log | 4.0 | 232 | 0.0402 | 0.0402 | 0.2005 | 0.0745 | 0.8389 | 103.3228 |
|
59 |
+
| No log | 5.0 | 290 | 0.0337 | 0.0337 | 0.1836 | 0.0665 | 0.8650 | 101.0925 |
|
60 |
+
| No log | 6.0 | 348 | 0.0327 | 0.0327 | 0.1808 | 0.0618 | 0.8691 | 101.2324 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.21.0
|
66 |
+
- Pytorch 1.12.0+cu113
|
67 |
+
- Datasets 2.4.0
|
68 |
+
- Tokenizers 0.12.1
|