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
9e7dd8f
•
1 Parent(s): fe96753

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: 0.6081143924159805
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: 0.2209
33
- - Spearmanr: 0.6081
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: 11
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
- | 6.3796 | 0.93 | 7 | 2.2462 | 0.2021 |
68
- | 1.2421 | 1.93 | 14 | 0.7066 | 0.1024 |
69
- | 0.7978 | 2.93 | 21 | 0.6895 | 0.1444 |
70
- | 0.7613 | 3.93 | 28 | 0.6758 | 0.2527 |
71
- | 0.7498 | 4.93 | 35 | 0.6772 | 0.2620 |
72
- | 0.7486 | 5.93 | 42 | 0.6703 | 0.3991 |
73
- | 0.7394 | 6.93 | 49 | 0.6506 | 0.4038 |
74
- | 0.8251 | 7.93 | 56 | 1.3414 | 0.3358 |
75
- | 0.8479 | 8.93 | 63 | 0.6745 | 0.3353 |
76
- | 0.7954 | 9.93 | 70 | 0.6610 | 0.4157 |
77
- | 0.7316 | 10.93 | 77 | 0.4977 | 0.4483 |
78
- | 0.6027 | 11.93 | 84 | 0.4138 | 0.4517 |
79
- | 0.5239 | 12.93 | 91 | 0.4185 | 0.4798 |
80
- | 0.4802 | 13.93 | 98 | 0.3637 | 0.5082 |
81
- | 0.5417 | 14.93 | 105 | 0.3360 | 0.5143 |
82
- | 0.5022 | 15.93 | 112 | 0.5404 | 0.5207 |
83
- | 0.4487 | 16.93 | 119 | 0.4884 | 0.5347 |
84
- | 0.4229 | 17.93 | 126 | 0.2941 | 0.5530 |
85
- | 0.3785 | 18.93 | 133 | 0.2920 | 0.5625 |
86
- | 0.3448 | 19.93 | 140 | 0.3082 | 0.5589 |
87
- | 0.3352 | 20.93 | 147 | 0.3006 | 0.5638 |
88
- | 0.3219 | 21.93 | 154 | 0.2707 | 0.5737 |
89
- | 0.3156 | 22.93 | 161 | 0.2623 | 0.5775 |
90
- | 0.3142 | 23.93 | 168 | 0.3162 | 0.5752 |
91
- | 0.3003 | 24.93 | 175 | 0.2487 | 0.5897 |
92
- | 0.303 | 25.93 | 182 | 0.2633 | 0.5981 |
93
- | 0.2757 | 26.93 | 189 | 0.2813 | 0.5921 |
94
- | 0.2836 | 27.93 | 196 | 0.2696 | 0.5968 |
95
- | 0.2759 | 28.93 | 203 | 0.2230 | 0.6060 |
96
- | 0.232 | 29.93 | 210 | 0.2209 | 0.6081 |
97
 
98
 
99
  ### Framework versions
 
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
 
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
  - 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
 
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