Hugging Face's logo

cradle-bio
/
tape-fluorescence-prediction-tape-fluorescence-evotuning-DistilProtBert

Text Classification
Transformers
PyTorch
bert
protein language model
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
thundaa commited on
Commit
a19823e
•
1 Parent(s): adeba7f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -34
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Spearmanr
21
  type: spearmanr
22
- value: 0.6085202769301487
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [thundaa/tape-fluorescence-evotuning-DistilProtBert](https://huggingface.co/thundaa/tape-fluorescence-evotuning-DistilProtBert) on the cradle-bio/tape-fluorescence dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.2716
33
- - Spearmanr: 0.6085
34
 
35
  ## Model description
36
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
52
  - learning_rate: 5e-05
53
  - train_batch_size: 40
54
  - eval_batch_size: 40
55
- - seed: 17
56
  - gradient_accumulation_steps: 64
57
  - total_train_batch_size: 2560
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -64,36 +64,36 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Spearmanr |
66
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
67
- | 5.9308 | 0.93 | 7 | 1.6932 | 0.0822 |
68
- | 1.0148 | 1.93 | 14 | 0.7407 | 0.1233 |
69
- | 0.7748 | 2.93 | 21 | 0.7388 | 0.3237 |
70
- | 0.7444 | 3.93 | 28 | 0.8205 | 0.4712 |
71
- | 0.7623 | 4.93 | 35 | 0.7168 | 0.4582 |
72
- | 0.7117 | 5.93 | 42 | 0.6898 | 0.4839 |
73
- | 0.7987 | 6.93 | 49 | 1.1860 | 0.3994 |
74
- | 0.8235 | 7.93 | 56 | 0.7290 | 0.4122 |
75
- | 1.0447 | 8.93 | 63 | 1.8475 | 0.4169 |
76
- | 0.9244 | 9.93 | 70 | 0.8985 | 0.4361 |
77
- | 0.7392 | 10.93 | 77 | 0.7053 | 0.4709 |
78
- | 0.5879 | 11.93 | 84 | 0.4930 | 0.4761 |
79
- | 0.5723 | 12.93 | 91 | 0.9298 | 0.4765 |
80
- | 0.7221 | 13.93 | 98 | 0.9479 | 0.4866 |
81
- | 1.0731 | 14.93 | 105 | 0.5306 | 0.5040 |
82
- | 0.5242 | 15.93 | 112 | 0.6331 | 0.4938 |
83
- | 0.5606 | 16.93 | 119 | 0.4096 | 0.5060 |
84
- | 0.5314 | 17.93 | 126 | 0.5781 | 0.5130 |
85
- | 0.4384 | 18.93 | 133 | 0.3880 | 0.5393 |
86
- | 0.4117 | 19.93 | 140 | 0.4584 | 0.5504 |
87
- | 0.4387 | 20.93 | 147 | 0.3611 | 0.5674 |
88
- | 0.3613 | 21.93 | 154 | 0.4159 | 0.5806 |
89
- | 0.5157 | 22.93 | 161 | 0.4041 | 0.5869 |
90
- | 0.4049 | 23.93 | 168 | 0.3187 | 0.5888 |
91
- | 0.3318 | 24.93 | 175 | 0.3206 | 0.5889 |
92
- | 0.3317 | 25.93 | 182 | 0.2964 | 0.5941 |
93
- | 0.303 | 26.93 | 189 | 0.2803 | 0.6006 |
94
- | 0.3058 | 27.93 | 196 | 0.2758 | 0.6042 |
95
- | 0.2988 | 28.93 | 203 | 0.3016 | 0.6049 |
96
- | 0.2814 | 29.93 | 210 | 0.2716 | 0.6085 |
97
 
98
 
99
  ### Framework versions
 
19
  metrics:
20
  - name: Spearmanr
21
  type: spearmanr
22
+ value: 0.5505486770316164
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [thundaa/tape-fluorescence-evotuning-DistilProtBert](https://huggingface.co/thundaa/tape-fluorescence-evotuning-DistilProtBert) on the cradle-bio/tape-fluorescence dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.3377
33
+ - Spearmanr: 0.5505
34
 
35
  ## Model description
36
 
 
52
  - learning_rate: 5e-05
53
  - train_batch_size: 40
54
  - eval_batch_size: 40
55
+ - seed: 42
56
  - gradient_accumulation_steps: 64
57
  - total_train_batch_size: 2560
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Spearmanr |
66
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
67
+ | 6.2764 | 0.93 | 7 | 1.9927 | -0.0786 |
68
+ | 1.1206 | 1.93 | 14 | 0.8223 | -0.1543 |
69
+ | 0.8054 | 2.93 | 21 | 0.6894 | 0.2050 |
70
+ | 0.7692 | 3.93 | 28 | 0.8084 | 0.2807 |
71
+ | 0.7597 | 4.93 | 35 | 0.6613 | 0.4003 |
72
+ | 0.7416 | 5.93 | 42 | 0.6803 | 0.3829 |
73
+ | 0.7256 | 6.93 | 49 | 0.6428 | 0.4416 |
74
+ | 0.6966 | 7.93 | 56 | 0.6086 | 0.4506 |
75
+ | 0.7603 | 8.93 | 63 | 0.9119 | 0.4697 |
76
+ | 0.9187 | 9.93 | 70 | 0.6048 | 0.4757 |
77
+ | 1.0371 | 10.93 | 77 | 2.0742 | 0.4076 |
78
+ | 1.0947 | 11.93 | 84 | 0.6633 | 0.4522 |
79
+ | 0.6946 | 12.93 | 91 | 0.6008 | 0.4123 |
80
+ | 0.6618 | 13.93 | 98 | 0.5931 | 0.4457 |
81
+ | 0.8635 | 14.93 | 105 | 1.9561 | 0.4331 |
82
+ | 0.9444 | 15.93 | 112 | 0.5627 | 0.5041 |
83
+ | 0.5535 | 16.93 | 119 | 0.4348 | 0.4840 |
84
+ | 0.9059 | 17.93 | 126 | 0.6704 | 0.5123 |
85
+ | 0.5693 | 18.93 | 133 | 0.4616 | 0.5285 |
86
+ | 0.6298 | 19.93 | 140 | 0.6915 | 0.5166 |
87
+ | 0.955 | 20.93 | 147 | 0.6679 | 0.5677 |
88
+ | 0.7866 | 21.93 | 154 | 0.8136 | 0.5559 |
89
+ | 0.6687 | 22.93 | 161 | 0.4782 | 0.5561 |
90
+ | 0.5336 | 23.93 | 168 | 0.4447 | 0.5499 |
91
+ | 0.4673 | 24.93 | 175 | 0.4258 | 0.5428 |
92
+ | 0.478 | 25.93 | 182 | 0.3651 | 0.5329 |
93
+ | 0.4023 | 26.93 | 189 | 0.3688 | 0.5428 |
94
+ | 0.3961 | 27.93 | 196 | 0.3692 | 0.5509 |
95
+ | 0.3808 | 28.93 | 203 | 0.3434 | 0.5514 |
96
+ | 0.3433 | 29.93 | 210 | 0.3377 | 0.5505 |
97
 
98
 
99
  ### Framework versions