Hugging Face's logo

Svetlana0303
/
Regression_xlnet_aug_CustomLoss

Text Classification
Transformers
PyTorch
TensorFlow
TensorBoard
xlnet
generated_from_keras_callback
Model card Files Metrics Community
1
Svetlana0303 commited on
Commit
578c1ba
·
1 Parent(s): 4704864

Upload TFXLNetForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.3652
18
- - Train Mae: 0.5686
19
- - Train Mse: 0.4521
20
- - Train R2-score: 0.7022
21
- - Validation Loss: 0.3538
22
- - Validation Mae: 0.5478
23
- - Validation Mse: 0.4335
24
- - Validation R2-score: 0.7272
25
  - Epoch: 14
26
 
27
  ## Model description
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
48
 
49
  | Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
50
  |:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
51
- | 0.3976 | 0.5843 | 0.4994 | 0.6170 | 0.3698 | 0.6232 | 0.4576 | 0.5391 | 0 |
52
- | 0.3938 | 0.5830 | 0.4901 | 0.5860 | 0.4330 | 0.6806 | 0.5537 | 0.2841 | 1 |
53
- | 0.3822 | 0.5739 | 0.4691 | -2.6800 | 0.3660 | 0.5198 | 0.4614 | 0.7579 | 2 |
54
- | 0.3716 | 0.5723 | 0.4607 | -0.3420 | 0.3541 | 0.5461 | 0.4343 | 0.7295 | 3 |
55
- | 0.3852 | 0.5794 | 0.4793 | 0.6654 | 0.3524 | 0.5654 | 0.4288 | 0.6982 | 4 |
56
- | 0.3826 | 0.5782 | 0.4787 | 0.5114 | 0.3584 | 0.5991 | 0.4374 | 0.6172 | 5 |
57
- | 0.3817 | 0.5746 | 0.4754 | 0.6431 | 0.3569 | 0.5945 | 0.4348 | 0.6304 | 6 |
58
- | 0.3705 | 0.5689 | 0.4541 | 0.6679 | 0.3621 | 0.5210 | 0.4528 | 0.7540 | 7 |
59
- | 0.3719 | 0.5654 | 0.4567 | 0.6807 | 0.3544 | 0.5446 | 0.4350 | 0.7315 | 8 |
60
- | 0.3752 | 0.5698 | 0.4638 | 0.6324 | 0.3571 | 0.5343 | 0.4413 | 0.7433 | 9 |
61
- | 0.3773 | 0.5714 | 0.4655 | 0.7523 | 0.3534 | 0.5787 | 0.4294 | 0.6701 | 10 |
62
- | 0.3651 | 0.5615 | 0.4490 | 0.6223 | 0.3766 | 0.5372 | 0.4846 | 0.7600 | 11 |
63
- | 0.3706 | 0.5649 | 0.4529 | 0.5998 | 0.3525 | 0.5683 | 0.4286 | 0.6924 | 12 |
64
- | 0.3779 | 0.5687 | 0.4619 | 0.6900 | 0.3532 | 0.5771 | 0.4291 | 0.6737 | 13 |
65
- | 0.3652 | 0.5686 | 0.4521 | 0.7022 | 0.3538 | 0.5478 | 0.4335 | 0.7272 | 14 |
66
 
67
 
68
  ### Framework versions
69
 
70
  - Transformers 4.28.1
71
  - TensorFlow 2.12.0
72
- - Datasets 2.11.0
73
  - Tokenizers 0.13.3
 
14
 
15
  This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.2430
18
+ - Train Mae: 0.5316
19
+ - Train Mse: 0.4353
20
+ - Train R2-score: 0.4207
21
+ - Validation Loss: 0.2455
22
+ - Validation Mae: 0.5751
23
+ - Validation Mse: 0.4288
24
+ - Validation R2-score: 0.6784
25
  - Epoch: 14
26
 
27
  ## Model description
 
48
 
49
  | Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
50
  |:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
51
+ | 0.2950 | 0.5789 | 0.4896 | 0.6909 | 0.2512 | 0.5341 | 0.4801 | 0.7603 | 0 |
52
+ | 0.2659 | 0.5516 | 0.4538 | 0.7145 | 0.2828 | 0.5680 | 0.5282 | 0.7477 | 1 |
53
+ | 0.2656 | 0.5492 | 0.4587 | 0.6858 | 0.2337 | 0.5345 | 0.4412 | 0.7431 | 2 |
54
+ | 0.2563 | 0.5484 | 0.4490 | 0.7247 | 0.2413 | 0.5202 | 0.4619 | 0.7581 | 3 |
55
+ | 0.2589 | 0.5511 | 0.4542 | 0.6757 | 0.2411 | 0.5199 | 0.4615 | 0.7580 | 4 |
56
+ | 0.2537 | 0.5407 | 0.4437 | 0.7605 | 0.2359 | 0.5244 | 0.4495 | 0.7517 | 5 |
57
+ | 0.2494 | 0.5385 | 0.4399 | 0.7668 | 0.2510 | 0.5821 | 0.4301 | 0.6621 | 6 |
58
+ | 0.2495 | 0.5403 | 0.4424 | 0.7765 | 0.2360 | 0.5242 | 0.4496 | 0.7519 | 7 |
59
+ | 0.2501 | 0.5394 | 0.4383 | 0.5209 | 0.2349 | 0.5279 | 0.4464 | 0.7491 | 8 |
60
+ | 0.2446 | 0.5343 | 0.4346 | 0.7534 | 0.2366 | 0.5585 | 0.4298 | 0.7105 | 9 |
61
+ | 0.2439 | 0.5316 | 0.4323 | 0.7561 | 0.2543 | 0.5376 | 0.4853 | 0.7599 | 10 |
62
+ | 0.2415 | 0.5348 | 0.4330 | 0.7928 | 0.2341 | 0.5316 | 0.4434 | 0.7459 | 11 |
63
+ | 0.2408 | 0.5323 | 0.4289 | 0.7827 | 0.2346 | 0.5291 | 0.4454 | 0.7481 | 12 |
64
+ | 0.2499 | 0.5392 | 0.4410 | 0.6008 | 0.2364 | 0.5230 | 0.4508 | 0.7527 | 13 |
65
+ | 0.2430 | 0.5316 | 0.4353 | 0.4207 | 0.2455 | 0.5751 | 0.4288 | 0.6784 | 14 |
66
 
67
 
68
  ### Framework versions
69
 
70
  - Transformers 4.28.1
71
  - TensorFlow 2.12.0
72
+ - Datasets 2.12.0
73
  - Tokenizers 0.13.3
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c7195d7f0b091346512a582bb130c9865eb2d4f2b3c02e3f30afcc5648a4e69
3
  size 469445640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae24f735475345f1ee67e93fa07dc15ba4fa70708c7c4d3c03273cd39abe7bc3
3
  size 469445640