Update README.md
Browse files
README.md
CHANGED
|
@@ -13,72 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# cyber_regression_model
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.0306
|
| 19 |
-
- Mse: 0.0306
|
| 20 |
-
- Mae: 0.1453
|
| 21 |
-
- R2: 0.7738
|
| 22 |
-
|
| 23 |
-
## Model description
|
| 24 |
-
|
| 25 |
-
More information needed
|
| 26 |
-
|
| 27 |
-
## Intended uses & limitations
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
-
|
| 37 |
-
### Training hyperparameters
|
| 38 |
-
|
| 39 |
-
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate: 2e-05
|
| 41 |
-
- train_batch_size: 16
|
| 42 |
-
- eval_batch_size: 16
|
| 43 |
-
- seed: 42
|
| 44 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
-
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs: 30
|
| 47 |
-
|
| 48 |
-
### Training results
|
| 49 |
-
|
| 50 |
-
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 |
|
| 51 |
-
|:-------------:|:-----:|:------:|:---------------:|:------:|:------:|:------:|
|
| 52 |
-
| 0.013 | 1.0 | 10304 | 0.0306 | 0.0306 | 0.1453 | 0.7738 |
|
| 53 |
-
| 0.0093 | 2.0 | 20608 | 0.0101 | 0.0101 | 0.0676 | 0.9252 |
|
| 54 |
-
| 0.0064 | 3.0 | 30912 | 0.0124 | 0.0124 | 0.0791 | 0.9080 |
|
| 55 |
-
| 0.0048 | 4.0 | 41216 | 0.0096 | 0.0096 | 0.0706 | 0.9291 |
|
| 56 |
-
| 0.0039 | 5.0 | 51520 | 0.0076 | 0.0076 | 0.0568 | 0.9438 |
|
| 57 |
-
| 0.0033 | 6.0 | 61824 | 0.0090 | 0.0090 | 0.0603 | 0.9336 |
|
| 58 |
-
| 0.0035 | 7.0 | 72128 | 0.0074 | 0.0074 | 0.0548 | 0.9455 |
|
| 59 |
-
| 0.0024 | 8.0 | 82432 | 0.0073 | 0.0073 | 0.0504 | 0.9460 |
|
| 60 |
-
| 0.002 | 9.0 | 92736 | 0.0068 | 0.0068 | 0.0495 | 0.9494 |
|
| 61 |
-
| 0.0018 | 10.0 | 103040 | 0.0073 | 0.0073 | 0.0525 | 0.9459 |
|
| 62 |
-
| 0.0016 | 11.0 | 113344 | 0.0067 | 0.0067 | 0.0470 | 0.9507 |
|
| 63 |
-
| 0.0013 | 12.0 | 123648 | 0.0068 | 0.0068 | 0.0512 | 0.9499 |
|
| 64 |
-
| 0.0013 | 13.0 | 133952 | 0.0076 | 0.0076 | 0.0557 | 0.9435 |
|
| 65 |
-
| 0.0012 | 14.0 | 144256 | 0.0066 | 0.0066 | 0.0493 | 0.9508 |
|
| 66 |
-
| 0.0009 | 15.0 | 154560 | 0.0069 | 0.0069 | 0.0476 | 0.9492 |
|
| 67 |
-
| 0.0009 | 16.0 | 164864 | 0.0065 | 0.0065 | 0.0479 | 0.9517 |
|
| 68 |
-
| 0.0008 | 17.0 | 175168 | 0.0067 | 0.0067 | 0.0476 | 0.9502 |
|
| 69 |
-
| 0.0007 | 18.0 | 185472 | 0.0075 | 0.0075 | 0.0530 | 0.9445 |
|
| 70 |
-
| 0.0006 | 19.0 | 195776 | 0.0067 | 0.0067 | 0.0495 | 0.9508 |
|
| 71 |
-
| 0.0006 | 20.0 | 206080 | 0.0068 | 0.0068 | 0.0485 | 0.9500 |
|
| 72 |
-
| 0.0004 | 21.0 | 216384 | 0.0066 | 0.0066 | 0.0452 | 0.9512 |
|
| 73 |
-
| 0.0004 | 22.0 | 226688 | 0.0071 | 0.0071 | 0.0506 | 0.9473 |
|
| 74 |
-
| 0.0003 | 23.0 | 236992 | 0.0069 | 0.0069 | 0.0490 | 0.9492 |
|
| 75 |
-
| 0.0003 | 24.0 | 247296 | 0.0068 | 0.0068 | 0.0468 | 0.9495 |
|
| 76 |
-
| 0.0003 | 25.0 | 257600 | 0.0067 | 0.0067 | 0.0474 | 0.9501 |
|
| 77 |
-
| 0.0002 | 26.0 | 267904 | 0.0068 | 0.0068 | 0.0477 | 0.9498 |
|
| 78 |
-
| 0.0002 | 27.0 | 278208 | 0.0070 | 0.0070 | 0.0486 | 0.9482 |
|
| 79 |
-
| 0.0002 | 28.0 | 288512 | 0.0067 | 0.0067 | 0.0469 | 0.9503 |
|
| 80 |
-
| 0.0001 | 29.0 | 298816 | 0.0068 | 0.0068 | 0.0478 | 0.9497 |
|
| 81 |
-
| 0.0002 | 30.0 | 309120 | 0.0068 | 0.0068 | 0.0473 | 0.9498 |
|
| 82 |
|
| 83 |
|
| 84 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
# cyber_regression_model
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
### Framework versions
|