Hugging Face's logo

tanoManzo
/
nucleotide-transformer-v2-100m-multi-species_ft_BioS2_1kbpHG19_DHSs_H3K27AC

Safetensors
esm
Generated from Trainer
custom_code
Model card Files Community
tanoManzo commited on
Commit
9aae64a
·
verified ·
1 Parent(s): 272e32f

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -34
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-100m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5466
23
- - F1 Score: 0.8621
24
- - Precision: 0.8285
25
- - Recall: 0.8987
26
- - Accuracy: 0.8520
27
- - Auc: 0.9239
28
- - Prc: 0.9156
29
 
30
  ## Model description
31
 
@@ -55,33 +55,24 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
59
- |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
60
- | 0.5763 | 0.0839 | 500 | 0.5065 | 0.7984 | 0.7182 | 0.8987 | 0.7663 | 0.8463 | 0.8263 |
61
- | 0.504 | 0.1677 | 1000 | 0.4523 | 0.8013 | 0.7794 | 0.8244 | 0.7895 | 0.8658 | 0.8544 |
62
- | 0.4788 | 0.2516 | 1500 | 0.4340 | 0.8121 | 0.7941 | 0.8309 | 0.8020 | 0.8811 | 0.8704 |
63
- | 0.4472 | 0.3355 | 2000 | 0.4096 | 0.8159 | 0.8239 | 0.8081 | 0.8123 | 0.8964 | 0.8910 |
64
- | 0.4406 | 0.4193 | 2500 | 0.4141 | 0.8355 | 0.7635 | 0.9225 | 0.8130 | 0.8986 | 0.8886 |
65
- | 0.4166 | 0.5032 | 3000 | 0.4071 | 0.7987 | 0.8636 | 0.7429 | 0.8072 | 0.9064 | 0.8999 |
66
- | 0.4138 | 0.5871 | 3500 | 0.3780 | 0.8417 | 0.8126 | 0.8729 | 0.8309 | 0.9116 | 0.9076 |
67
- | 0.3913 | 0.6709 | 4000 | 0.4063 | 0.8176 | 0.8699 | 0.7713 | 0.8228 | 0.9121 | 0.9100 |
68
- | 0.3933 | 0.7548 | 4500 | 0.4189 | 0.8422 | 0.7628 | 0.9400 | 0.8187 | 0.9195 | 0.9149 |
69
- | 0.3877 | 0.8386 | 5000 | 0.3575 | 0.8516 | 0.8181 | 0.8879 | 0.8406 | 0.9217 | 0.9193 |
70
- | 0.3629 | 0.9225 | 5500 | 0.3722 | 0.8462 | 0.8641 | 0.8289 | 0.8448 | 0.9269 | 0.9247 |
71
- | 0.3687 | 1.0064 | 6000 | 0.3571 | 0.8571 | 0.8093 | 0.9110 | 0.8437 | 0.9295 | 0.9276 |
72
- | 0.3221 | 1.0902 | 6500 | 0.4058 | 0.8584 | 0.8291 | 0.8899 | 0.8489 | 0.9294 | 0.9259 |
73
- | 0.323 | 1.1741 | 7000 | 0.4120 | 0.8596 | 0.8007 | 0.9280 | 0.8440 | 0.9274 | 0.9234 |
74
- | 0.3258 | 1.2580 | 7500 | 0.4037 | 0.8514 | 0.8561 | 0.8469 | 0.8478 | 0.9261 | 0.9257 |
75
- | 0.323 | 1.3418 | 8000 | 0.3856 | 0.8586 | 0.8396 | 0.8785 | 0.8510 | 0.9277 | 0.9252 |
76
- | 0.3074 | 1.4257 | 8500 | 0.4192 | 0.8611 | 0.8082 | 0.9215 | 0.8470 | 0.9312 | 0.9292 |
77
- | 0.3156 | 1.5096 | 9000 | 0.3983 | 0.8608 | 0.8477 | 0.8742 | 0.8544 | 0.9328 | 0.9326 |
78
- | 0.3118 | 1.5934 | 9500 | 0.4275 | 0.8496 | 0.8780 | 0.8231 | 0.8500 | 0.9322 | 0.9306 |
79
- | 0.3319 | 1.6773 | 10000 | 0.3792 | 0.8626 | 0.8361 | 0.8908 | 0.8539 | 0.9323 | 0.9314 |
80
- | 0.3178 | 1.7612 | 10500 | 0.4414 | 0.8568 | 0.8698 | 0.8442 | 0.8547 | 0.9337 | 0.9321 |
81
- | 0.3255 | 1.8450 | 11000 | 0.3767 | 0.8694 | 0.8445 | 0.8957 | 0.8614 | 0.9350 | 0.9318 |
82
- | 0.317 | 1.9289 | 11500 | 0.4115 | 0.8663 | 0.8158 | 0.9234 | 0.8532 | 0.9342 | 0.9309 |
83
- | 0.2921 | 2.0127 | 12000 | 0.4654 | 0.8616 | 0.8591 | 0.8641 | 0.8571 | 0.9345 | 0.9322 |
84
- | 0.2203 | 2.0966 | 12500 | 0.5466 | 0.8621 | 0.8285 | 0.8987 | 0.8520 | 0.9239 | 0.9156 |
85
 
86
 
87
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-100m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3735
23
+ - F1 Score: 0.8587
24
+ - Precision: 0.8425
25
+ - Recall: 0.8754
26
+ - Accuracy: 0.8487
27
+ - Auc: 0.9238
28
+ - Prc: 0.9216
29
 
30
  ## Model description
31
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
59
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
60
+ | 0.5667 | 0.0840 | 500 | 0.5015 | 0.7975 | 0.7265 | 0.8838 | 0.7643 | 0.8328 | 0.8048 |
61
+ | 0.4953 | 0.1681 | 1000 | 0.4806 | 0.8157 | 0.7288 | 0.9260 | 0.7803 | 0.8607 | 0.8304 |
62
+ | 0.4666 | 0.2521 | 1500 | 0.4297 | 0.8321 | 0.7856 | 0.8844 | 0.8126 | 0.8818 | 0.8659 |
63
+ | 0.4404 | 0.3362 | 2000 | 0.4224 | 0.8267 | 0.8060 | 0.8485 | 0.8132 | 0.8860 | 0.8693 |
64
+ | 0.4366 | 0.4202 | 2500 | 0.4054 | 0.8393 | 0.7599 | 0.9372 | 0.8116 | 0.9012 | 0.8936 |
65
+ | 0.4145 | 0.5043 | 3000 | 0.3880 | 0.8276 | 0.8491 | 0.8072 | 0.8235 | 0.9060 | 0.8967 |
66
+ | 0.408 | 0.5883 | 3500 | 0.3836 | 0.8360 | 0.8481 | 0.8242 | 0.8302 | 0.9105 | 0.9063 |
67
+ | 0.3924 | 0.6724 | 4000 | 0.4161 | 0.8444 | 0.7698 | 0.9350 | 0.8191 | 0.9053 | 0.8972 |
68
+ | 0.3858 | 0.7564 | 4500 | 0.4237 | 0.8432 | 0.7774 | 0.9212 | 0.8201 | 0.9114 | 0.9041 |
69
+ | 0.3781 | 0.8405 | 5000 | 0.3678 | 0.8446 | 0.8435 | 0.8457 | 0.8366 | 0.9169 | 0.9082 |
70
+ | 0.3915 | 0.9245 | 5500 | 0.4415 | 0.8158 | 0.8908 | 0.7525 | 0.8217 | 0.9192 | 0.9156 |
71
+ | 0.3862 | 1.0086 | 6000 | 0.4456 | 0.8584 | 0.8201 | 0.9004 | 0.8440 | 0.9106 | 0.8937 |
72
+ | 0.3313 | 1.0926 | 6500 | 0.3869 | 0.8593 | 0.8335 | 0.8866 | 0.8475 | 0.9234 | 0.9158 |
73
+ | 0.3144 | 1.1767 | 7000 | 0.4080 | 0.8581 | 0.8527 | 0.8636 | 0.8501 | 0.9266 | 0.9210 |
74
+ | 0.3239 | 1.2607 | 7500 | 0.3974 | 0.8515 | 0.8587 | 0.8444 | 0.8454 | 0.9239 | 0.9188 |
75
+ | 0.3446 | 1.3448 | 8000 | 0.3735 | 0.8587 | 0.8425 | 0.8754 | 0.8487 | 0.9238 | 0.9216 |
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11647a911a429a240bb9b574bc45c9da27b562779ddc71c3a663baa09940e089
3
  size 383169868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3212659b0312926364ca081e9919754d50c9cf9299ee0f48592c2a2f67a1c1be
3
  size 383169868