Hugging Face's logo

tanoManzo
/
gena-lm-bert-base-t2t-multi_ft_BioS74_1kbpHG19_DHSs_H3K27AC

Safetensors
bert
Generated from Trainer
custom_code
Model card Files Community
tanoManzo commited on
Commit
0ed7a47
·
verified ·
1 Parent(s): f806026

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -26
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-base-t2t-multi](https://huggingface.co/AIRI-Institute/gena-lm-bert-base-t2t-multi) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5006
22
- - F1 Score: 0.8354
23
- - Precision: 0.7947
24
- - Recall: 0.8805
25
- - Accuracy: 0.8183
26
- - Auc: 0.8820
27
- - Prc: 0.8475
28
 
29
  ## Model description
30
 
@@ -56,25 +56,21 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
59
- | 0.7035 | 0.1314 | 500 | 0.6627 | 0.7293 | 0.5961 | 0.9392 | 0.6350 | 0.7403 | 0.7568 |
60
- | 0.6574 | 0.2629 | 1000 | 0.5876 | 0.7377 | 0.7815 | 0.6986 | 0.7399 | 0.8086 | 0.8004 |
61
- | 0.5656 | 0.3943 | 1500 | 0.5193 | 0.7822 | 0.7711 | 0.7936 | 0.7686 | 0.8457 | 0.8246 |
62
- | 0.5073 | 0.5258 | 2000 | 0.4790 | 0.8163 | 0.7550 | 0.8885 | 0.7907 | 0.8535 | 0.8218 |
63
- | 0.4742 | 0.6572 | 2500 | 0.4942 | 0.8198 | 0.7632 | 0.8855 | 0.7962 | 0.8618 | 0.8403 |
64
- | 0.4972 | 0.7886 | 3000 | 0.4656 | 0.8266 | 0.7614 | 0.9041 | 0.8015 | 0.8676 | 0.8439 |
65
- | 0.4617 | 0.9201 | 3500 | 0.4728 | 0.8308 | 0.7787 | 0.8905 | 0.8101 | 0.8728 | 0.8534 |
66
- | 0.4659 | 1.0515 | 4000 | 0.5274 | 0.7788 | 0.8388 | 0.7268 | 0.7839 | 0.8769 | 0.8621 |
67
- | 0.4604 | 1.1830 | 4500 | 0.4604 | 0.8263 | 0.7852 | 0.8719 | 0.8080 | 0.8802 | 0.8660 |
68
- | 0.4592 | 1.3144 | 5000 | 0.4634 | 0.8151 | 0.8144 | 0.8157 | 0.8062 | 0.8860 | 0.8719 |
69
- | 0.451 | 1.4458 | 5500 | 0.4865 | 0.8174 | 0.8165 | 0.8182 | 0.8086 | 0.8856 | 0.8731 |
70
- | 0.4372 | 1.5773 | 6000 | 0.4993 | 0.8333 | 0.7882 | 0.8840 | 0.8149 | 0.8783 | 0.8563 |
71
- | 0.4654 | 1.7087 | 6500 | 0.4827 | 0.8290 | 0.7884 | 0.8739 | 0.8112 | 0.8852 | 0.8694 |
72
- | 0.4419 | 1.8402 | 7000 | 0.4670 | 0.8358 | 0.7951 | 0.8810 | 0.8188 | 0.8886 | 0.8696 |
73
- | 0.4501 | 1.9716 | 7500 | 0.4731 | 0.8337 | 0.7810 | 0.8940 | 0.8133 | 0.8859 | 0.8601 |
74
- | 0.4351 | 2.1030 | 8000 | 0.4699 | 0.8326 | 0.7845 | 0.8870 | 0.8133 | 0.8722 | 0.8249 |
75
- | 0.4337 | 2.2345 | 8500 | 0.4711 | 0.8275 | 0.8123 | 0.8433 | 0.8159 | 0.8846 | 0.8509 |
76
- | 0.4368 | 2.3659 | 9000 | 0.5160 | 0.7900 | 0.8514 | 0.7368 | 0.7949 | 0.8936 | 0.8752 |
77
- | 0.4077 | 2.4974 | 9500 | 0.5006 | 0.8354 | 0.7947 | 0.8805 | 0.8183 | 0.8820 | 0.8475 |
78
 
79
 
80
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-base-t2t-multi](https://huggingface.co/AIRI-Institute/gena-lm-bert-base-t2t-multi) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4695
22
+ - F1 Score: 0.8296
23
+ - Precision: 0.8049
24
+ - Recall: 0.8559
25
+ - Accuracy: 0.8159
26
+ - Auc: 0.8884
27
+ - Prc: 0.8698
28
 
29
  ## Model description
30
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
59
+ | 0.6932 | 0.1314 | 500 | 0.6750 | 0.7557 | 0.6451 | 0.9121 | 0.6913 | 0.7738 | 0.7686 |
60
+ | 0.6827 | 0.2629 | 1000 | 0.6411 | 0.7193 | 0.7791 | 0.6680 | 0.7271 | 0.8011 | 0.7937 |
61
+ | 0.6017 | 0.3943 | 1500 | 0.5240 | 0.7905 | 0.7499 | 0.8358 | 0.7681 | 0.8219 | 0.7799 |
62
+ | 0.5244 | 0.5258 | 2000 | 0.4895 | 0.8144 | 0.7511 | 0.8895 | 0.7878 | 0.8434 | 0.8158 |
63
+ | 0.4828 | 0.6572 | 2500 | 0.5271 | 0.8173 | 0.7274 | 0.9327 | 0.7818 | 0.8456 | 0.8206 |
64
+ | 0.4956 | 0.7886 | 3000 | 0.4738 | 0.8208 | 0.7613 | 0.8905 | 0.7965 | 0.8684 | 0.8455 |
65
+ | 0.4734 | 0.9201 | 3500 | 0.5137 | 0.8169 | 0.7383 | 0.9141 | 0.7854 | 0.8494 | 0.8056 |
66
+ | 0.4941 | 1.0515 | 4000 | 0.4861 | 0.8191 | 0.7850 | 0.8564 | 0.8020 | 0.8684 | 0.8406 |
67
+ | 0.4698 | 1.1830 | 4500 | 0.4819 | 0.8240 | 0.7594 | 0.9006 | 0.7986 | 0.8712 | 0.8431 |
68
+ | 0.4771 | 1.3144 | 5000 | 0.4686 | 0.8304 | 0.7681 | 0.9036 | 0.8067 | 0.8663 | 0.8222 |
69
+ | 0.4621 | 1.4458 | 5500 | 0.4901 | 0.8164 | 0.8088 | 0.8242 | 0.8059 | 0.8722 | 0.8383 |
70
+ | 0.4558 | 1.5773 | 6000 | 0.5173 | 0.8261 | 0.7868 | 0.8694 | 0.8083 | 0.8718 | 0.8432 |
71
+ | 0.4543 | 1.7087 | 6500 | 0.4865 | 0.8287 | 0.7592 | 0.9121 | 0.8025 | 0.8729 | 0.8363 |
72
+ | 0.4559 | 1.8402 | 7000 | 0.4634 | 0.8270 | 0.8085 | 0.8463 | 0.8146 | 0.8691 | 0.8258 |
73
+ | 0.456 | 1.9716 | 7500 | 0.4695 | 0.8296 | 0.8049 | 0.8559 | 0.8159 | 0.8884 | 0.8698 |
 
 
 
 
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeacfa6f1bd25e1fcb27ba61fb8a1800e7d3c37f0d89cfb30e16eb45a308904d
3
  size 442503040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c859406b5962257dcb7513bc505e3e4b59e4d37e176e560cb5fa78e297b32b
3
  size 442503040