Hugging Face's logo

tanoManzo
/
gena-lm-bigbird-base-t2t_ft_BioS2_1kbpHG19_DHSs_H3K27AC

Safetensors
big_bird
Generated from Trainer
Model card Files Community
tanoManzo commited on
Commit
5cc862f
·
verified ·
1 Parent(s): 9bbb835

End of training

Browse files
Files changed (2) hide show
  1. README.md +33 -28
  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-bigbird-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bigbird-base-t2t) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4425
22
- - F1 Score: 0.8721
23
- - Precision: 0.8249
24
- - Recall: 0.9251
25
- - Accuracy: 0.8582
26
- - Auc: 0.9367
27
- - Prc: 0.9328
28
 
29
  ## Model description
30
 
@@ -54,27 +54,32 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
58
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
59
- | 0.5218 | 0.0840 | 500 | 0.4577 | 0.7891 | 0.8196 | 0.7608 | 0.7874 | 0.8723 | 0.8607 |
60
- | 0.4698 | 0.1680 | 1000 | 0.4514 | 0.8273 | 0.7836 | 0.8762 | 0.8087 | 0.8879 | 0.8785 |
61
- | 0.448 | 0.2521 | 1500 | 0.4550 | 0.8350 | 0.8002 | 0.8730 | 0.8197 | 0.8978 | 0.8886 |
62
- | 0.4463 | 0.3361 | 2000 | 0.4247 | 0.8392 | 0.7616 | 0.9344 | 0.8128 | 0.9076 | 0.9047 |
63
- | 0.4264 | 0.4201 | 2500 | 0.4020 | 0.8010 | 0.8781 | 0.7364 | 0.8087 | 0.9130 | 0.9101 |
64
- | 0.401 | 0.5041 | 3000 | 0.3818 | 0.8560 | 0.7897 | 0.9344 | 0.8356 | 0.9223 | 0.9200 |
65
- | 0.4035 | 0.5881 | 3500 | 0.3980 | 0.8590 | 0.7956 | 0.9335 | 0.8398 | 0.9232 | 0.9183 |
66
- | 0.3774 | 0.6722 | 4000 | 0.3752 | 0.8543 | 0.8404 | 0.8685 | 0.8450 | 0.9259 | 0.9245 |
67
- | 0.3985 | 0.7562 | 4500 | 0.4618 | 0.8360 | 0.8660 | 0.8081 | 0.8343 | 0.9243 | 0.9251 |
68
- | 0.387 | 0.8402 | 5000 | 0.3753 | 0.8641 | 0.8377 | 0.8923 | 0.8533 | 0.9310 | 0.9299 |
69
- | 0.3907 | 0.9242 | 5500 | 0.3589 | 0.8537 | 0.8528 | 0.8547 | 0.8469 | 0.9284 | 0.9284 |
70
- | 0.3775 | 1.0082 | 6000 | 0.4544 | 0.8622 | 0.8517 | 0.8730 | 0.8541 | 0.9310 | 0.9296 |
71
- | 0.3507 | 1.0923 | 6500 | 0.4114 | 0.8722 | 0.8177 | 0.9344 | 0.8568 | 0.9326 | 0.9246 |
72
- | 0.3476 | 1.1763 | 7000 | 0.4028 | 0.8747 | 0.8442 | 0.9074 | 0.8640 | 0.9354 | 0.9348 |
73
- | 0.3676 | 1.2603 | 7500 | 0.3671 | 0.8684 | 0.8487 | 0.8891 | 0.8592 | 0.9362 | 0.9358 |
74
- | 0.3651 | 1.3443 | 8000 | 0.3837 | 0.8713 | 0.8418 | 0.9029 | 0.8605 | 0.9369 | 0.9364 |
75
- | 0.3468 | 1.4283 | 8500 | 0.4281 | 0.8648 | 0.8491 | 0.8811 | 0.8560 | 0.9342 | 0.9309 |
76
- | 0.3447 | 1.5124 | 9000 | 0.3955 | 0.8727 | 0.8171 | 0.9364 | 0.8571 | 0.9387 | 0.9380 |
77
- | 0.35 | 1.5964 | 9500 | 0.4425 | 0.8721 | 0.8249 | 0.9251 | 0.8582 | 0.9367 | 0.9328 |
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [AIRI-Institute/gena-lm-bigbird-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bigbird-base-t2t) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4554
22
+ - F1 Score: 0.8794
23
+ - Precision: 0.8386
24
+ - Recall: 0.9243
25
+ - Accuracy: 0.8677
26
+ - Auc: 0.9401
27
+ - Prc: 0.9344
28
 
29
  ## Model description
30
 
 
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc | Prc |
58
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
59
+ | 0.5309 | 0.0840 | 500 | 0.4610 | 0.8214 | 0.7592 | 0.8947 | 0.7969 | 0.8757 | 0.8625 |
60
+ | 0.4688 | 0.1681 | 1000 | 0.4717 | 0.8298 | 0.7467 | 0.9336 | 0.8001 | 0.8862 | 0.8753 |
61
+ | 0.4569 | 0.2521 | 1500 | 0.4326 | 0.8304 | 0.7461 | 0.9362 | 0.8005 | 0.8889 | 0.8752 |
62
+ | 0.4361 | 0.3361 | 2000 | 0.4337 | 0.8186 | 0.8527 | 0.7870 | 0.8180 | 0.9035 | 0.8988 |
63
+ | 0.4222 | 0.4202 | 2500 | 0.4968 | 0.8434 | 0.7628 | 0.9430 | 0.8173 | 0.9095 | 0.8979 |
64
+ | 0.4233 | 0.5042 | 3000 | 0.3891 | 0.8396 | 0.8674 | 0.8135 | 0.8378 | 0.9207 | 0.9177 |
65
+ | 0.4031 | 0.5882 | 3500 | 0.3743 | 0.8564 | 0.8687 | 0.8444 | 0.8522 | 0.9262 | 0.9231 |
66
+ | 0.3739 | 0.6723 | 4000 | 0.3970 | 0.8520 | 0.8662 | 0.8383 | 0.8480 | 0.9275 | 0.9269 |
67
+ | 0.3891 | 0.7563 | 4500 | 0.4361 | 0.7852 | 0.9181 | 0.6859 | 0.8042 | 0.9277 | 0.9273 |
68
+ | 0.3856 | 0.8403 | 5000 | 0.3882 | 0.8518 | 0.8904 | 0.8164 | 0.8517 | 0.9309 | 0.9306 |
69
+ | 0.3926 | 0.9244 | 5500 | 0.3291 | 0.8693 | 0.8600 | 0.8789 | 0.8622 | 0.9328 | 0.9320 |
70
+ | 0.3737 | 1.0084 | 6000 | 0.3546 | 0.8571 | 0.8783 | 0.8370 | 0.8544 | 0.9331 | 0.9329 |
71
+ | 0.346 | 1.0924 | 6500 | 0.4352 | 0.8719 | 0.8378 | 0.9088 | 0.8606 | 0.9345 | 0.9317 |
72
+ | 0.3355 | 1.1765 | 7000 | 0.3880 | 0.8665 | 0.8560 | 0.8773 | 0.8590 | 0.9362 | 0.9350 |
73
+ | 0.3452 | 1.2605 | 7500 | 0.3991 | 0.8737 | 0.8279 | 0.9249 | 0.8605 | 0.9376 | 0.9368 |
74
+ | 0.3618 | 1.3445 | 8000 | 0.3564 | 0.8645 | 0.8804 | 0.8492 | 0.8612 | 0.9381 | 0.9382 |
75
+ | 0.3335 | 1.4286 | 8500 | 0.4719 | 0.8376 | 0.9110 | 0.7751 | 0.8432 | 0.9381 | 0.9381 |
76
+ | 0.3671 | 1.5126 | 9000 | 0.3808 | 0.8748 | 0.8607 | 0.8895 | 0.8672 | 0.9404 | 0.9405 |
77
+ | 0.3505 | 1.5966 | 9500 | 0.4061 | 0.8801 | 0.8690 | 0.8914 | 0.8733 | 0.9403 | 0.9405 |
78
+ | 0.3602 | 1.6807 | 10000 | 0.4968 | 0.8485 | 0.9112 | 0.7938 | 0.8521 | 0.9409 | 0.9412 |
79
+ | 0.348 | 1.7647 | 10500 | 0.4114 | 0.8781 | 0.8319 | 0.9298 | 0.8654 | 0.9403 | 0.9369 |
80
+ | 0.3435 | 1.8487 | 11000 | 0.3816 | 0.8745 | 0.8828 | 0.8663 | 0.8702 | 0.9415 | 0.9399 |
81
+ | 0.3701 | 1.9328 | 11500 | 0.3733 | 0.8641 | 0.8865 | 0.8428 | 0.8617 | 0.9395 | 0.9369 |
82
+ | 0.3281 | 2.0168 | 12000 | 0.4554 | 0.8794 | 0.8386 | 0.9243 | 0.8677 | 0.9401 | 0.9344 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f35dbe1984f090b457d954ed803aaa69b6a050c8fd5c1bbbde5b4f14400492a
3
  size 455871688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc29a07a5e440f2dd5926c46d9c9de90442b35a121f36a4ed0160c01c095f092
3
  size 455871688