update model card README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ model-index:
|
|
19 |
metrics:
|
20 |
- name: Spearmanr
|
21 |
type: spearmanr
|
22 |
-
value: 0.
|
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.
|
33 |
-
- Spearmanr: 0.
|
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:
|
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.
|
68 |
-
| 1.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
|
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
|
98 |
|
99 |
### Framework versions
|
|
|
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 |
|
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 |
- 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 |
|
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
|