|
--- |
|
base_model: aubmindlab/bert-base-arabertv02 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: arabert_cross_relevance_task7_fold5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# arabert_cross_relevance_task7_fold5 |
|
|
|
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2737 |
|
- Qwk: 0.2531 |
|
- Mse: 0.2737 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| No log | 0.125 | 2 | 1.2635 | 0.0075 | 1.2635 | |
|
| No log | 0.25 | 4 | 0.4733 | 0.0856 | 0.4733 | |
|
| No log | 0.375 | 6 | 0.4780 | 0.1193 | 0.4780 | |
|
| No log | 0.5 | 8 | 0.4171 | 0.1125 | 0.4171 | |
|
| No log | 0.625 | 10 | 0.3393 | 0.1154 | 0.3393 | |
|
| No log | 0.75 | 12 | 0.3133 | 0.0877 | 0.3133 | |
|
| No log | 0.875 | 14 | 0.2954 | 0.0958 | 0.2954 | |
|
| No log | 1.0 | 16 | 0.2822 | 0.1293 | 0.2822 | |
|
| No log | 1.125 | 18 | 0.2616 | 0.1948 | 0.2616 | |
|
| No log | 1.25 | 20 | 0.2545 | 0.2304 | 0.2545 | |
|
| No log | 1.375 | 22 | 0.2454 | 0.2207 | 0.2454 | |
|
| No log | 1.5 | 24 | 0.2508 | 0.2316 | 0.2508 | |
|
| No log | 1.625 | 26 | 0.2477 | 0.2028 | 0.2477 | |
|
| No log | 1.75 | 28 | 0.2442 | 0.2000 | 0.2442 | |
|
| No log | 1.875 | 30 | 0.2513 | 0.2028 | 0.2513 | |
|
| No log | 2.0 | 32 | 0.2468 | 0.2138 | 0.2468 | |
|
| No log | 2.125 | 34 | 0.2358 | 0.2349 | 0.2358 | |
|
| No log | 2.25 | 36 | 0.2333 | 0.2259 | 0.2333 | |
|
| No log | 2.375 | 38 | 0.2391 | 0.2212 | 0.2391 | |
|
| No log | 2.5 | 40 | 0.2305 | 0.2355 | 0.2305 | |
|
| No log | 2.625 | 42 | 0.2393 | 0.2837 | 0.2393 | |
|
| No log | 2.75 | 44 | 0.2395 | 0.2837 | 0.2395 | |
|
| No log | 2.875 | 46 | 0.2326 | 0.2838 | 0.2326 | |
|
| No log | 3.0 | 48 | 0.2323 | 0.2435 | 0.2323 | |
|
| No log | 3.125 | 50 | 0.2326 | 0.2723 | 0.2326 | |
|
| No log | 3.25 | 52 | 0.2331 | 0.2723 | 0.2331 | |
|
| No log | 3.375 | 54 | 0.2328 | 0.2800 | 0.2328 | |
|
| No log | 3.5 | 56 | 0.2397 | 0.2677 | 0.2397 | |
|
| No log | 3.625 | 58 | 0.2444 | 0.2503 | 0.2444 | |
|
| No log | 3.75 | 60 | 0.2477 | 0.2371 | 0.2477 | |
|
| No log | 3.875 | 62 | 0.2481 | 0.2355 | 0.2481 | |
|
| No log | 4.0 | 64 | 0.2561 | 0.2148 | 0.2561 | |
|
| No log | 4.125 | 66 | 0.2682 | 0.2101 | 0.2682 | |
|
| No log | 4.25 | 68 | 0.2759 | 0.1725 | 0.2759 | |
|
| No log | 4.375 | 70 | 0.2719 | 0.1665 | 0.2719 | |
|
| No log | 4.5 | 72 | 0.2545 | 0.2022 | 0.2545 | |
|
| No log | 4.625 | 74 | 0.2459 | 0.2488 | 0.2459 | |
|
| No log | 4.75 | 76 | 0.2442 | 0.2674 | 0.2442 | |
|
| No log | 4.875 | 78 | 0.2574 | 0.2183 | 0.2574 | |
|
| No log | 5.0 | 80 | 0.2695 | 0.2133 | 0.2695 | |
|
| No log | 5.125 | 82 | 0.2908 | 0.2237 | 0.2908 | |
|
| No log | 5.25 | 84 | 0.2741 | 0.2523 | 0.2741 | |
|
| No log | 5.375 | 86 | 0.2535 | 0.2795 | 0.2535 | |
|
| No log | 5.5 | 88 | 0.2511 | 0.2795 | 0.2511 | |
|
| No log | 5.625 | 90 | 0.2503 | 0.2680 | 0.2503 | |
|
| No log | 5.75 | 92 | 0.2516 | 0.2536 | 0.2516 | |
|
| No log | 5.875 | 94 | 0.2541 | 0.2575 | 0.2541 | |
|
| No log | 6.0 | 96 | 0.2541 | 0.2575 | 0.2541 | |
|
| No log | 6.125 | 98 | 0.2569 | 0.2609 | 0.2569 | |
|
| No log | 6.25 | 100 | 0.2577 | 0.2609 | 0.2577 | |
|
| No log | 6.375 | 102 | 0.2619 | 0.2609 | 0.2619 | |
|
| No log | 6.5 | 104 | 0.2736 | 0.2575 | 0.2736 | |
|
| No log | 6.625 | 106 | 0.2782 | 0.2575 | 0.2782 | |
|
| No log | 6.75 | 108 | 0.2718 | 0.2793 | 0.2718 | |
|
| No log | 6.875 | 110 | 0.2666 | 0.2575 | 0.2666 | |
|
| No log | 7.0 | 112 | 0.2601 | 0.2575 | 0.2601 | |
|
| No log | 7.125 | 114 | 0.2517 | 0.2605 | 0.2517 | |
|
| No log | 7.25 | 116 | 0.2515 | 0.2641 | 0.2515 | |
|
| No log | 7.375 | 118 | 0.2527 | 0.2641 | 0.2527 | |
|
| No log | 7.5 | 120 | 0.2579 | 0.2565 | 0.2579 | |
|
| No log | 7.625 | 122 | 0.2612 | 0.2644 | 0.2612 | |
|
| No log | 7.75 | 124 | 0.2592 | 0.2644 | 0.2592 | |
|
| No log | 7.875 | 126 | 0.2572 | 0.2682 | 0.2572 | |
|
| No log | 8.0 | 128 | 0.2594 | 0.2682 | 0.2594 | |
|
| No log | 8.125 | 130 | 0.2600 | 0.2682 | 0.2600 | |
|
| No log | 8.25 | 132 | 0.2633 | 0.2609 | 0.2633 | |
|
| No log | 8.375 | 134 | 0.2691 | 0.2496 | 0.2691 | |
|
| No log | 8.5 | 136 | 0.2714 | 0.2426 | 0.2714 | |
|
| No log | 8.625 | 138 | 0.2651 | 0.2609 | 0.2651 | |
|
| No log | 8.75 | 140 | 0.2593 | 0.2682 | 0.2593 | |
|
| No log | 8.875 | 142 | 0.2587 | 0.2682 | 0.2587 | |
|
| No log | 9.0 | 144 | 0.2587 | 0.2682 | 0.2587 | |
|
| No log | 9.125 | 146 | 0.2620 | 0.2682 | 0.2620 | |
|
| No log | 9.25 | 148 | 0.2666 | 0.2570 | 0.2666 | |
|
| No log | 9.375 | 150 | 0.2697 | 0.2570 | 0.2697 | |
|
| No log | 9.5 | 152 | 0.2714 | 0.2570 | 0.2714 | |
|
| No log | 9.625 | 154 | 0.2724 | 0.2531 | 0.2724 | |
|
| No log | 9.75 | 156 | 0.2735 | 0.2458 | 0.2735 | |
|
| No log | 9.875 | 158 | 0.2736 | 0.2531 | 0.2736 | |
|
| No log | 10.0 | 160 | 0.2737 | 0.2531 | 0.2737 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
