update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: predict-perception-bertino-focus-object
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# predict-perception-bertino-focus-object
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [indigo-ai/BERTino](https://huggingface.co/indigo-ai/BERTino) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2766
|
| 18 |
+
- R2: 0.5460
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 20
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 1996
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 47
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss | R2 |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 49 |
+
| 0.4798 | 1.0 | 14 | 0.4519 | 0.2581 |
|
| 50 |
+
| 0.2481 | 2.0 | 28 | 0.3042 | 0.5007 |
|
| 51 |
+
| 0.12 | 3.0 | 42 | 0.3746 | 0.3851 |
|
| 52 |
+
| 0.0969 | 4.0 | 56 | 0.3186 | 0.4770 |
|
| 53 |
+
| 0.0907 | 5.0 | 70 | 0.3727 | 0.3882 |
|
| 54 |
+
| 0.0673 | 6.0 | 84 | 0.2847 | 0.5327 |
|
| 55 |
+
| 0.0457 | 7.0 | 98 | 0.3141 | 0.4844 |
|
| 56 |
+
| 0.0431 | 8.0 | 112 | 0.3369 | 0.4470 |
|
| 57 |
+
| 0.028 | 9.0 | 126 | 0.3039 | 0.5012 |
|
| 58 |
+
| 0.0244 | 10.0 | 140 | 0.2964 | 0.5135 |
|
| 59 |
+
| 0.0201 | 11.0 | 154 | 0.3072 | 0.4958 |
|
| 60 |
+
| 0.0153 | 12.0 | 168 | 0.3049 | 0.4995 |
|
| 61 |
+
| 0.0155 | 13.0 | 182 | 0.2924 | 0.5201 |
|
| 62 |
+
| 0.015 | 14.0 | 196 | 0.2585 | 0.5757 |
|
| 63 |
+
| 0.0181 | 15.0 | 210 | 0.3258 | 0.4652 |
|
| 64 |
+
| 0.0136 | 16.0 | 224 | 0.3142 | 0.4842 |
|
| 65 |
+
| 0.0105 | 17.0 | 238 | 0.2536 | 0.5837 |
|
| 66 |
+
| 0.0104 | 18.0 | 252 | 0.2407 | 0.6050 |
|
| 67 |
+
| 0.0107 | 19.0 | 266 | 0.2727 | 0.5524 |
|
| 68 |
+
| 0.0084 | 20.0 | 280 | 0.3117 | 0.4883 |
|
| 69 |
+
| 0.0102 | 21.0 | 294 | 0.2999 | 0.5078 |
|
| 70 |
+
| 0.0074 | 22.0 | 308 | 0.3018 | 0.5047 |
|
| 71 |
+
| 0.0068 | 23.0 | 322 | 0.2826 | 0.5361 |
|
| 72 |
+
| 0.0054 | 24.0 | 336 | 0.2804 | 0.5398 |
|
| 73 |
+
| 0.0044 | 25.0 | 350 | 0.2912 | 0.5220 |
|
| 74 |
+
| 0.0048 | 26.0 | 364 | 0.2813 | 0.5382 |
|
| 75 |
+
| 0.005 | 27.0 | 378 | 0.2933 | 0.5186 |
|
| 76 |
+
| 0.0046 | 28.0 | 392 | 0.2820 | 0.5371 |
|
| 77 |
+
| 0.004 | 29.0 | 406 | 0.2717 | 0.5541 |
|
| 78 |
+
| 0.0054 | 30.0 | 420 | 0.2717 | 0.5540 |
|
| 79 |
+
| 0.0042 | 31.0 | 434 | 0.2699 | 0.5570 |
|
| 80 |
+
| 0.0033 | 32.0 | 448 | 0.2630 | 0.5684 |
|
| 81 |
+
| 0.0038 | 33.0 | 462 | 0.2578 | 0.5767 |
|
| 82 |
+
| 0.0032 | 34.0 | 476 | 0.2687 | 0.5589 |
|
| 83 |
+
| 0.004 | 35.0 | 490 | 0.2737 | 0.5507 |
|
| 84 |
+
| 0.0031 | 36.0 | 504 | 0.2753 | 0.5481 |
|
| 85 |
+
| 0.0037 | 37.0 | 518 | 0.2819 | 0.5373 |
|
| 86 |
+
| 0.0034 | 38.0 | 532 | 0.2759 | 0.5471 |
|
| 87 |
+
| 0.0034 | 39.0 | 546 | 0.2835 | 0.5347 |
|
| 88 |
+
| 0.0029 | 40.0 | 560 | 0.2814 | 0.5381 |
|
| 89 |
+
| 0.0033 | 41.0 | 574 | 0.2801 | 0.5403 |
|
| 90 |
+
| 0.0025 | 42.0 | 588 | 0.2759 | 0.5472 |
|
| 91 |
+
| 0.0029 | 43.0 | 602 | 0.2790 | 0.5421 |
|
| 92 |
+
| 0.0028 | 44.0 | 616 | 0.2801 | 0.5401 |
|
| 93 |
+
| 0.003 | 45.0 | 630 | 0.2772 | 0.5451 |
|
| 94 |
+
| 0.0028 | 46.0 | 644 | 0.2764 | 0.5463 |
|
| 95 |
+
| 0.0026 | 47.0 | 658 | 0.2766 | 0.5460 |
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
### Framework versions
|
| 99 |
+
|
| 100 |
+
- Transformers 4.16.2
|
| 101 |
+
- Pytorch 1.10.2+cu113
|
| 102 |
+
- Datasets 1.18.3
|
| 103 |
+
- Tokenizers 0.11.0
|