thundaa commited on
Commit
5045d00
1 Parent(s): 9a74efa

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - protein language model
5
+ - generated_from_trainer
6
+ datasets:
7
+ - train
8
+ metrics:
9
+ - spearmanr
10
+ model-index:
11
+ - name: tape-fluorescence-prediction-RITA_s
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: cradle-bio/tape-fluorescence
18
+ type: train
19
+ metrics:
20
+ - name: Spearmanr
21
+ type: spearmanr
22
+ value: 0.22463833322952328
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # tape-fluorescence-prediction-RITA_s
29
+
30
+ This model is a fine-tuned version of [lightonai/RITA_s](https://huggingface.co/lightonai/RITA_s) on the cradle-bio/tape-fluorescence dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.6701
33
+ - Spearmanr: 0.2246
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-05
53
+ - train_batch_size: 32
54
+ - eval_batch_size: 32
55
+ - seed: 42
56
+ - gradient_accumulation_steps: 128
57
+ - total_train_batch_size: 4096
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 15
61
+ - mixed_precision_training: Native AMP
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Spearmanr |
66
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
67
+ | 6.8975 | 0.85 | 4 | 0.7033 | -0.0855 |
68
+ | 1.2475 | 1.85 | 8 | 0.7764 | 0.0752 |
69
+ | 0.934 | 2.85 | 12 | 0.6740 | 0.0423 |
70
+ | 0.8294 | 3.85 | 16 | 0.6732 | 0.1257 |
71
+ | 0.8274 | 4.85 | 20 | 0.6826 | 0.1877 |
72
+ | 0.8333 | 5.85 | 24 | 0.6838 | 0.1494 |
73
+ | 0.8287 | 6.85 | 28 | 0.6800 | 0.1292 |
74
+ | 0.8278 | 7.85 | 32 | 0.6777 | 0.1293 |
75
+ | 0.8267 | 8.85 | 36 | 0.6749 | 0.1349 |
76
+ | 0.8275 | 9.85 | 40 | 0.6794 | 0.1942 |
77
+ | 0.8276 | 10.85 | 44 | 0.6728 | 0.1639 |
78
+ | 0.8245 | 11.85 | 48 | 0.6721 | 0.1776 |
79
+ | 0.823 | 12.85 | 52 | 0.6715 | 0.1874 |
80
+ | 0.822 | 13.85 | 56 | 0.6707 | 0.1731 |
81
+ | 0.7005 | 14.85 | 60 | 0.6701 | 0.2246 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.18.0
87
+ - Pytorch 1.11.0
88
+ - Datasets 2.1.0
89
+ - Tokenizers 0.12.1