Training in progress, step 500
Browse files- README.md +319 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_task2_organization
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k15_task2_organization
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.5737
|
| 19 |
+
- Qwk: 0.3877
|
| 20 |
+
- Mse: 0.5737
|
| 21 |
+
- Rmse: 0.7574
|
| 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: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 100
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:------:|
|
| 52 |
+
| No log | 0.0253 | 2 | 4.3690 | -0.0267 | 4.3690 | 2.0902 |
|
| 53 |
+
| No log | 0.0506 | 4 | 2.4003 | 0.0288 | 2.4003 | 1.5493 |
|
| 54 |
+
| No log | 0.0759 | 6 | 1.5507 | -0.0787 | 1.5507 | 1.2453 |
|
| 55 |
+
| No log | 0.1013 | 8 | 1.0078 | -0.0545 | 1.0078 | 1.0039 |
|
| 56 |
+
| No log | 0.1266 | 10 | 1.1063 | 0.0492 | 1.1063 | 1.0518 |
|
| 57 |
+
| No log | 0.1519 | 12 | 1.0854 | 0.0971 | 1.0854 | 1.0418 |
|
| 58 |
+
| No log | 0.1772 | 14 | 0.8576 | 0.1359 | 0.8576 | 0.9261 |
|
| 59 |
+
| No log | 0.2025 | 16 | 0.8127 | 0.1497 | 0.8127 | 0.9015 |
|
| 60 |
+
| No log | 0.2278 | 18 | 0.7885 | 0.1758 | 0.7885 | 0.8880 |
|
| 61 |
+
| No log | 0.2532 | 20 | 0.8173 | 0.1539 | 0.8173 | 0.9040 |
|
| 62 |
+
| No log | 0.2785 | 22 | 0.8129 | 0.1725 | 0.8129 | 0.9016 |
|
| 63 |
+
| No log | 0.3038 | 24 | 0.7687 | 0.2558 | 0.7687 | 0.8767 |
|
| 64 |
+
| No log | 0.3291 | 26 | 0.7662 | 0.1543 | 0.7662 | 0.8753 |
|
| 65 |
+
| No log | 0.3544 | 28 | 0.7731 | 0.1997 | 0.7731 | 0.8793 |
|
| 66 |
+
| No log | 0.3797 | 30 | 0.7848 | 0.1879 | 0.7848 | 0.8859 |
|
| 67 |
+
| No log | 0.4051 | 32 | 0.8358 | 0.1537 | 0.8358 | 0.9142 |
|
| 68 |
+
| No log | 0.4304 | 34 | 0.9089 | 0.0627 | 0.9089 | 0.9534 |
|
| 69 |
+
| No log | 0.4557 | 36 | 0.9320 | 0.0627 | 0.9320 | 0.9654 |
|
| 70 |
+
| No log | 0.4810 | 38 | 0.8017 | 0.2127 | 0.8017 | 0.8954 |
|
| 71 |
+
| No log | 0.5063 | 40 | 0.7716 | 0.2398 | 0.7716 | 0.8784 |
|
| 72 |
+
| No log | 0.5316 | 42 | 0.7756 | 0.2974 | 0.7756 | 0.8807 |
|
| 73 |
+
| No log | 0.5570 | 44 | 0.8389 | 0.2357 | 0.8389 | 0.9159 |
|
| 74 |
+
| No log | 0.5823 | 46 | 1.0205 | 0.1658 | 1.0205 | 1.0102 |
|
| 75 |
+
| No log | 0.6076 | 48 | 1.1705 | 0.2464 | 1.1705 | 1.0819 |
|
| 76 |
+
| No log | 0.6329 | 50 | 1.0921 | 0.2146 | 1.0921 | 1.0450 |
|
| 77 |
+
| No log | 0.6582 | 52 | 0.8905 | 0.2194 | 0.8905 | 0.9437 |
|
| 78 |
+
| No log | 0.6835 | 54 | 0.8647 | 0.3480 | 0.8647 | 0.9299 |
|
| 79 |
+
| No log | 0.7089 | 56 | 0.8326 | 0.2942 | 0.8326 | 0.9125 |
|
| 80 |
+
| No log | 0.7342 | 58 | 0.8088 | 0.2255 | 0.8088 | 0.8993 |
|
| 81 |
+
| No log | 0.7595 | 60 | 0.8053 | 0.2364 | 0.8053 | 0.8974 |
|
| 82 |
+
| No log | 0.7848 | 62 | 0.8461 | 0.2511 | 0.8461 | 0.9198 |
|
| 83 |
+
| No log | 0.8101 | 64 | 0.7570 | 0.3056 | 0.7570 | 0.8701 |
|
| 84 |
+
| No log | 0.8354 | 66 | 0.7653 | 0.4231 | 0.7653 | 0.8748 |
|
| 85 |
+
| No log | 0.8608 | 68 | 0.8311 | 0.3704 | 0.8311 | 0.9116 |
|
| 86 |
+
| No log | 0.8861 | 70 | 0.7841 | 0.4353 | 0.7841 | 0.8855 |
|
| 87 |
+
| No log | 0.9114 | 72 | 0.7408 | 0.4260 | 0.7408 | 0.8607 |
|
| 88 |
+
| No log | 0.9367 | 74 | 0.7833 | 0.3387 | 0.7833 | 0.8851 |
|
| 89 |
+
| No log | 0.9620 | 76 | 0.8651 | 0.3678 | 0.8651 | 0.9301 |
|
| 90 |
+
| No log | 0.9873 | 78 | 0.7570 | 0.4043 | 0.7570 | 0.8701 |
|
| 91 |
+
| No log | 1.0127 | 80 | 0.7696 | 0.3855 | 0.7696 | 0.8773 |
|
| 92 |
+
| No log | 1.0380 | 82 | 0.9747 | 0.2800 | 0.9747 | 0.9873 |
|
| 93 |
+
| No log | 1.0633 | 84 | 0.8854 | 0.3802 | 0.8854 | 0.9409 |
|
| 94 |
+
| No log | 1.0886 | 86 | 0.8619 | 0.4278 | 0.8619 | 0.9284 |
|
| 95 |
+
| No log | 1.1139 | 88 | 0.9360 | 0.4359 | 0.9360 | 0.9675 |
|
| 96 |
+
| No log | 1.1392 | 90 | 0.9941 | 0.4210 | 0.9941 | 0.9970 |
|
| 97 |
+
| No log | 1.1646 | 92 | 1.0775 | 0.4011 | 1.0775 | 1.0380 |
|
| 98 |
+
| No log | 1.1899 | 94 | 1.2781 | 0.3528 | 1.2781 | 1.1305 |
|
| 99 |
+
| No log | 1.2152 | 96 | 1.0740 | 0.4313 | 1.0740 | 1.0364 |
|
| 100 |
+
| No log | 1.2405 | 98 | 0.8126 | 0.4415 | 0.8126 | 0.9014 |
|
| 101 |
+
| No log | 1.2658 | 100 | 0.8656 | 0.3780 | 0.8656 | 0.9303 |
|
| 102 |
+
| No log | 1.2911 | 102 | 0.8439 | 0.3587 | 0.8439 | 0.9186 |
|
| 103 |
+
| No log | 1.3165 | 104 | 0.7168 | 0.4249 | 0.7168 | 0.8467 |
|
| 104 |
+
| No log | 1.3418 | 106 | 0.7328 | 0.4341 | 0.7328 | 0.8561 |
|
| 105 |
+
| No log | 1.3671 | 108 | 0.7535 | 0.4448 | 0.7535 | 0.8680 |
|
| 106 |
+
| No log | 1.3924 | 110 | 0.8559 | 0.4002 | 0.8559 | 0.9251 |
|
| 107 |
+
| No log | 1.4177 | 112 | 0.7682 | 0.4196 | 0.7682 | 0.8765 |
|
| 108 |
+
| No log | 1.4430 | 114 | 0.6411 | 0.4146 | 0.6411 | 0.8007 |
|
| 109 |
+
| No log | 1.4684 | 116 | 0.8461 | 0.2985 | 0.8461 | 0.9198 |
|
| 110 |
+
| No log | 1.4937 | 118 | 0.7944 | 0.3088 | 0.7944 | 0.8913 |
|
| 111 |
+
| No log | 1.5190 | 120 | 0.6731 | 0.4864 | 0.6731 | 0.8204 |
|
| 112 |
+
| No log | 1.5443 | 122 | 1.0100 | 0.3419 | 1.0100 | 1.0050 |
|
| 113 |
+
| No log | 1.5696 | 124 | 1.0416 | 0.3522 | 1.0416 | 1.0206 |
|
| 114 |
+
| No log | 1.5949 | 126 | 0.8210 | 0.4528 | 0.8210 | 0.9061 |
|
| 115 |
+
| No log | 1.6203 | 128 | 0.6653 | 0.4379 | 0.6653 | 0.8157 |
|
| 116 |
+
| No log | 1.6456 | 130 | 0.6673 | 0.4053 | 0.6673 | 0.8169 |
|
| 117 |
+
| No log | 1.6709 | 132 | 0.6429 | 0.4531 | 0.6429 | 0.8018 |
|
| 118 |
+
| No log | 1.6962 | 134 | 0.6987 | 0.4007 | 0.6987 | 0.8359 |
|
| 119 |
+
| No log | 1.7215 | 136 | 0.7376 | 0.4324 | 0.7376 | 0.8588 |
|
| 120 |
+
| No log | 1.7468 | 138 | 0.8040 | 0.4501 | 0.8040 | 0.8967 |
|
| 121 |
+
| No log | 1.7722 | 140 | 0.6968 | 0.4705 | 0.6968 | 0.8348 |
|
| 122 |
+
| No log | 1.7975 | 142 | 0.6730 | 0.4162 | 0.6730 | 0.8204 |
|
| 123 |
+
| No log | 1.8228 | 144 | 0.6791 | 0.4162 | 0.6791 | 0.8241 |
|
| 124 |
+
| No log | 1.8481 | 146 | 0.7661 | 0.5250 | 0.7661 | 0.8753 |
|
| 125 |
+
| No log | 1.8734 | 148 | 0.8381 | 0.4292 | 0.8381 | 0.9155 |
|
| 126 |
+
| No log | 1.8987 | 150 | 0.6994 | 0.4876 | 0.6994 | 0.8363 |
|
| 127 |
+
| No log | 1.9241 | 152 | 0.6785 | 0.3402 | 0.6785 | 0.8237 |
|
| 128 |
+
| No log | 1.9494 | 154 | 1.0417 | 0.3375 | 1.0417 | 1.0207 |
|
| 129 |
+
| No log | 1.9747 | 156 | 1.1164 | 0.3486 | 1.1164 | 1.0566 |
|
| 130 |
+
| No log | 2.0 | 158 | 0.8267 | 0.4026 | 0.8267 | 0.9093 |
|
| 131 |
+
| No log | 2.0253 | 160 | 0.6474 | 0.3550 | 0.6474 | 0.8046 |
|
| 132 |
+
| No log | 2.0506 | 162 | 0.6492 | 0.4991 | 0.6492 | 0.8057 |
|
| 133 |
+
| No log | 2.0759 | 164 | 0.6474 | 0.5061 | 0.6474 | 0.8046 |
|
| 134 |
+
| No log | 2.1013 | 166 | 0.6874 | 0.5017 | 0.6874 | 0.8291 |
|
| 135 |
+
| No log | 2.1266 | 168 | 0.6801 | 0.5258 | 0.6801 | 0.8247 |
|
| 136 |
+
| No log | 2.1519 | 170 | 0.6492 | 0.5305 | 0.6492 | 0.8058 |
|
| 137 |
+
| No log | 2.1772 | 172 | 0.8048 | 0.4589 | 0.8048 | 0.8971 |
|
| 138 |
+
| No log | 2.2025 | 174 | 0.8810 | 0.4111 | 0.8810 | 0.9386 |
|
| 139 |
+
| No log | 2.2278 | 176 | 0.7792 | 0.4507 | 0.7792 | 0.8827 |
|
| 140 |
+
| No log | 2.2532 | 178 | 0.6345 | 0.4911 | 0.6345 | 0.7965 |
|
| 141 |
+
| No log | 2.2785 | 180 | 0.6162 | 0.4850 | 0.6162 | 0.7850 |
|
| 142 |
+
| No log | 2.3038 | 182 | 0.6445 | 0.4914 | 0.6445 | 0.8028 |
|
| 143 |
+
| No log | 2.3291 | 184 | 0.5888 | 0.4512 | 0.5888 | 0.7673 |
|
| 144 |
+
| No log | 2.3544 | 186 | 0.6185 | 0.4892 | 0.6185 | 0.7864 |
|
| 145 |
+
| No log | 2.3797 | 188 | 0.8369 | 0.4515 | 0.8369 | 0.9148 |
|
| 146 |
+
| No log | 2.4051 | 190 | 0.8616 | 0.4515 | 0.8616 | 0.9282 |
|
| 147 |
+
| No log | 2.4304 | 192 | 0.6999 | 0.4369 | 0.6999 | 0.8366 |
|
| 148 |
+
| No log | 2.4557 | 194 | 0.5669 | 0.4588 | 0.5669 | 0.7529 |
|
| 149 |
+
| No log | 2.4810 | 196 | 0.7155 | 0.4612 | 0.7155 | 0.8459 |
|
| 150 |
+
| No log | 2.5063 | 198 | 0.9914 | 0.4019 | 0.9914 | 0.9957 |
|
| 151 |
+
| No log | 2.5316 | 200 | 1.0791 | 0.3746 | 1.0791 | 1.0388 |
|
| 152 |
+
| No log | 2.5570 | 202 | 0.9067 | 0.4111 | 0.9067 | 0.9522 |
|
| 153 |
+
| No log | 2.5823 | 204 | 0.6566 | 0.5233 | 0.6566 | 0.8103 |
|
| 154 |
+
| No log | 2.6076 | 206 | 0.6460 | 0.5037 | 0.6460 | 0.8037 |
|
| 155 |
+
| No log | 2.6329 | 208 | 0.7618 | 0.4817 | 0.7618 | 0.8728 |
|
| 156 |
+
| No log | 2.6582 | 210 | 0.7891 | 0.4817 | 0.7891 | 0.8883 |
|
| 157 |
+
| No log | 2.6835 | 212 | 0.7039 | 0.5065 | 0.7039 | 0.8390 |
|
| 158 |
+
| No log | 2.7089 | 214 | 0.6188 | 0.4893 | 0.6188 | 0.7866 |
|
| 159 |
+
| No log | 2.7342 | 216 | 0.6936 | 0.4375 | 0.6936 | 0.8328 |
|
| 160 |
+
| No log | 2.7595 | 218 | 0.7765 | 0.4536 | 0.7765 | 0.8812 |
|
| 161 |
+
| No log | 2.7848 | 220 | 0.7218 | 0.4547 | 0.7218 | 0.8496 |
|
| 162 |
+
| No log | 2.8101 | 222 | 0.6558 | 0.4558 | 0.6558 | 0.8098 |
|
| 163 |
+
| No log | 2.8354 | 224 | 0.6126 | 0.5100 | 0.6126 | 0.7827 |
|
| 164 |
+
| No log | 2.8608 | 226 | 0.5983 | 0.5254 | 0.5983 | 0.7735 |
|
| 165 |
+
| No log | 2.8861 | 228 | 0.5896 | 0.5314 | 0.5896 | 0.7678 |
|
| 166 |
+
| No log | 2.9114 | 230 | 0.5985 | 0.5080 | 0.5985 | 0.7737 |
|
| 167 |
+
| No log | 2.9367 | 232 | 0.6732 | 0.4524 | 0.6732 | 0.8205 |
|
| 168 |
+
| No log | 2.9620 | 234 | 0.7100 | 0.5002 | 0.7100 | 0.8426 |
|
| 169 |
+
| No log | 2.9873 | 236 | 0.6388 | 0.4727 | 0.6388 | 0.7993 |
|
| 170 |
+
| No log | 3.0127 | 238 | 0.5867 | 0.5209 | 0.5867 | 0.7659 |
|
| 171 |
+
| No log | 3.0380 | 240 | 0.6296 | 0.5019 | 0.6296 | 0.7935 |
|
| 172 |
+
| No log | 3.0633 | 242 | 0.7182 | 0.5288 | 0.7182 | 0.8474 |
|
| 173 |
+
| No log | 3.0886 | 244 | 0.7035 | 0.4269 | 0.7035 | 0.8388 |
|
| 174 |
+
| No log | 3.1139 | 246 | 0.6429 | 0.3951 | 0.6429 | 0.8018 |
|
| 175 |
+
| No log | 3.1392 | 248 | 0.6112 | 0.4800 | 0.6112 | 0.7818 |
|
| 176 |
+
| No log | 3.1646 | 250 | 0.6252 | 0.4159 | 0.6252 | 0.7907 |
|
| 177 |
+
| No log | 3.1899 | 252 | 0.6577 | 0.4773 | 0.6577 | 0.8110 |
|
| 178 |
+
| No log | 3.2152 | 254 | 0.6440 | 0.4912 | 0.6440 | 0.8025 |
|
| 179 |
+
| No log | 3.2405 | 256 | 0.6327 | 0.4928 | 0.6327 | 0.7954 |
|
| 180 |
+
| No log | 3.2658 | 258 | 0.6422 | 0.5076 | 0.6422 | 0.8014 |
|
| 181 |
+
| No log | 3.2911 | 260 | 0.6207 | 0.4629 | 0.6207 | 0.7879 |
|
| 182 |
+
| No log | 3.3165 | 262 | 0.6054 | 0.4196 | 0.6054 | 0.7781 |
|
| 183 |
+
| No log | 3.3418 | 264 | 0.6066 | 0.4705 | 0.6066 | 0.7789 |
|
| 184 |
+
| No log | 3.3671 | 266 | 0.6575 | 0.4772 | 0.6575 | 0.8109 |
|
| 185 |
+
| No log | 3.3924 | 268 | 0.7084 | 0.5133 | 0.7084 | 0.8417 |
|
| 186 |
+
| No log | 3.4177 | 270 | 0.6969 | 0.5554 | 0.6969 | 0.8348 |
|
| 187 |
+
| No log | 3.4430 | 272 | 0.6363 | 0.5026 | 0.6363 | 0.7977 |
|
| 188 |
+
| No log | 3.4684 | 274 | 0.5901 | 0.5385 | 0.5901 | 0.7682 |
|
| 189 |
+
| No log | 3.4937 | 276 | 0.5857 | 0.5053 | 0.5857 | 0.7653 |
|
| 190 |
+
| No log | 3.5190 | 278 | 0.6352 | 0.4399 | 0.6352 | 0.7970 |
|
| 191 |
+
| No log | 3.5443 | 280 | 0.6184 | 0.4883 | 0.6184 | 0.7864 |
|
| 192 |
+
| No log | 3.5696 | 282 | 0.6330 | 0.5148 | 0.6330 | 0.7956 |
|
| 193 |
+
| No log | 3.5949 | 284 | 0.6498 | 0.5372 | 0.6498 | 0.8061 |
|
| 194 |
+
| No log | 3.6203 | 286 | 0.7095 | 0.5332 | 0.7095 | 0.8423 |
|
| 195 |
+
| No log | 3.6456 | 288 | 0.6901 | 0.5435 | 0.6901 | 0.8307 |
|
| 196 |
+
| No log | 3.6709 | 290 | 0.6327 | 0.5561 | 0.6327 | 0.7955 |
|
| 197 |
+
| No log | 3.6962 | 292 | 0.6139 | 0.5738 | 0.6139 | 0.7835 |
|
| 198 |
+
| No log | 3.7215 | 294 | 0.6042 | 0.5443 | 0.6042 | 0.7773 |
|
| 199 |
+
| No log | 3.7468 | 296 | 0.6355 | 0.5378 | 0.6355 | 0.7972 |
|
| 200 |
+
| No log | 3.7722 | 298 | 0.7193 | 0.4946 | 0.7193 | 0.8481 |
|
| 201 |
+
| No log | 3.7975 | 300 | 0.6755 | 0.5656 | 0.6755 | 0.8219 |
|
| 202 |
+
| No log | 3.8228 | 302 | 0.6392 | 0.5564 | 0.6392 | 0.7995 |
|
| 203 |
+
| No log | 3.8481 | 304 | 0.5992 | 0.5630 | 0.5992 | 0.7741 |
|
| 204 |
+
| No log | 3.8734 | 306 | 0.5781 | 0.5549 | 0.5781 | 0.7603 |
|
| 205 |
+
| No log | 3.8987 | 308 | 0.5818 | 0.5539 | 0.5818 | 0.7627 |
|
| 206 |
+
| No log | 3.9241 | 310 | 0.6319 | 0.5362 | 0.6319 | 0.7949 |
|
| 207 |
+
| No log | 3.9494 | 312 | 0.7864 | 0.4674 | 0.7864 | 0.8868 |
|
| 208 |
+
| No log | 3.9747 | 314 | 0.9048 | 0.3891 | 0.9048 | 0.9512 |
|
| 209 |
+
| No log | 4.0 | 316 | 0.8968 | 0.3837 | 0.8968 | 0.9470 |
|
| 210 |
+
| No log | 4.0253 | 318 | 0.7795 | 0.4393 | 0.7795 | 0.8829 |
|
| 211 |
+
| No log | 4.0506 | 320 | 0.6356 | 0.5536 | 0.6356 | 0.7973 |
|
| 212 |
+
| No log | 4.0759 | 322 | 0.6250 | 0.5641 | 0.6250 | 0.7906 |
|
| 213 |
+
| No log | 4.1013 | 324 | 0.6526 | 0.5015 | 0.6526 | 0.8078 |
|
| 214 |
+
| No log | 4.1266 | 326 | 0.6440 | 0.5168 | 0.6440 | 0.8025 |
|
| 215 |
+
| No log | 4.1519 | 328 | 0.6588 | 0.5649 | 0.6588 | 0.8116 |
|
| 216 |
+
| No log | 4.1772 | 330 | 0.7618 | 0.5162 | 0.7618 | 0.8728 |
|
| 217 |
+
| No log | 4.2025 | 332 | 0.8426 | 0.4454 | 0.8426 | 0.9179 |
|
| 218 |
+
| No log | 4.2278 | 334 | 0.7616 | 0.4869 | 0.7616 | 0.8727 |
|
| 219 |
+
| No log | 4.2532 | 336 | 0.6672 | 0.4793 | 0.6672 | 0.8169 |
|
| 220 |
+
| No log | 4.2785 | 338 | 0.5970 | 0.5046 | 0.5970 | 0.7727 |
|
| 221 |
+
| No log | 4.3038 | 340 | 0.6017 | 0.5046 | 0.6017 | 0.7757 |
|
| 222 |
+
| No log | 4.3291 | 342 | 0.6801 | 0.5239 | 0.6801 | 0.8247 |
|
| 223 |
+
| No log | 4.3544 | 344 | 0.7281 | 0.4926 | 0.7281 | 0.8533 |
|
| 224 |
+
| No log | 4.3797 | 346 | 0.7052 | 0.5196 | 0.7052 | 0.8398 |
|
| 225 |
+
| No log | 4.4051 | 348 | 0.6871 | 0.5196 | 0.6871 | 0.8289 |
|
| 226 |
+
| No log | 4.4304 | 350 | 0.6958 | 0.5098 | 0.6958 | 0.8341 |
|
| 227 |
+
| No log | 4.4557 | 352 | 0.7277 | 0.5192 | 0.7277 | 0.8530 |
|
| 228 |
+
| No log | 4.4810 | 354 | 0.6973 | 0.4873 | 0.6973 | 0.8350 |
|
| 229 |
+
| No log | 4.5063 | 356 | 0.6797 | 0.5135 | 0.6797 | 0.8244 |
|
| 230 |
+
| No log | 4.5316 | 358 | 0.6776 | 0.5119 | 0.6776 | 0.8232 |
|
| 231 |
+
| No log | 4.5570 | 360 | 0.6876 | 0.4785 | 0.6876 | 0.8292 |
|
| 232 |
+
| No log | 4.5823 | 362 | 0.6517 | 0.4841 | 0.6517 | 0.8073 |
|
| 233 |
+
| No log | 4.6076 | 364 | 0.6083 | 0.5080 | 0.6083 | 0.7800 |
|
| 234 |
+
| No log | 4.6329 | 366 | 0.5823 | 0.4714 | 0.5823 | 0.7631 |
|
| 235 |
+
| No log | 4.6582 | 368 | 0.5717 | 0.4935 | 0.5717 | 0.7561 |
|
| 236 |
+
| No log | 4.6835 | 370 | 0.5748 | 0.5192 | 0.5748 | 0.7581 |
|
| 237 |
+
| No log | 4.7089 | 372 | 0.5976 | 0.5111 | 0.5976 | 0.7731 |
|
| 238 |
+
| No log | 4.7342 | 374 | 0.6140 | 0.5216 | 0.6140 | 0.7836 |
|
| 239 |
+
| No log | 4.7595 | 376 | 0.5954 | 0.5290 | 0.5954 | 0.7716 |
|
| 240 |
+
| No log | 4.7848 | 378 | 0.6063 | 0.4943 | 0.6063 | 0.7786 |
|
| 241 |
+
| No log | 4.8101 | 380 | 0.6789 | 0.4198 | 0.6789 | 0.8239 |
|
| 242 |
+
| No log | 4.8354 | 382 | 0.6693 | 0.4112 | 0.6693 | 0.8181 |
|
| 243 |
+
| No log | 4.8608 | 384 | 0.6002 | 0.4623 | 0.6002 | 0.7747 |
|
| 244 |
+
| No log | 4.8861 | 386 | 0.5789 | 0.5245 | 0.5789 | 0.7609 |
|
| 245 |
+
| No log | 4.9114 | 388 | 0.5847 | 0.5629 | 0.5847 | 0.7646 |
|
| 246 |
+
| No log | 4.9367 | 390 | 0.5899 | 0.5569 | 0.5899 | 0.7680 |
|
| 247 |
+
| No log | 4.9620 | 392 | 0.6024 | 0.5221 | 0.6024 | 0.7761 |
|
| 248 |
+
| No log | 4.9873 | 394 | 0.6407 | 0.4817 | 0.6407 | 0.8004 |
|
| 249 |
+
| No log | 5.0127 | 396 | 0.6464 | 0.4551 | 0.6464 | 0.8040 |
|
| 250 |
+
| No log | 5.0380 | 398 | 0.6061 | 0.5103 | 0.6061 | 0.7785 |
|
| 251 |
+
| No log | 5.0633 | 400 | 0.5914 | 0.5539 | 0.5914 | 0.7690 |
|
| 252 |
+
| No log | 5.0886 | 402 | 0.5904 | 0.5090 | 0.5904 | 0.7684 |
|
| 253 |
+
| No log | 5.1139 | 404 | 0.5731 | 0.5006 | 0.5731 | 0.7570 |
|
| 254 |
+
| No log | 5.1392 | 406 | 0.5675 | 0.4620 | 0.5675 | 0.7533 |
|
| 255 |
+
| No log | 5.1646 | 408 | 0.5727 | 0.5100 | 0.5727 | 0.7568 |
|
| 256 |
+
| No log | 5.1899 | 410 | 0.5861 | 0.5440 | 0.5861 | 0.7655 |
|
| 257 |
+
| No log | 5.2152 | 412 | 0.5981 | 0.5502 | 0.5981 | 0.7733 |
|
| 258 |
+
| No log | 5.2405 | 414 | 0.6077 | 0.5560 | 0.6077 | 0.7795 |
|
| 259 |
+
| No log | 5.2658 | 416 | 0.6620 | 0.5475 | 0.6620 | 0.8136 |
|
| 260 |
+
| No log | 5.2911 | 418 | 0.6702 | 0.5597 | 0.6702 | 0.8187 |
|
| 261 |
+
| No log | 5.3165 | 420 | 0.6206 | 0.5558 | 0.6206 | 0.7878 |
|
| 262 |
+
| No log | 5.3418 | 422 | 0.5930 | 0.5616 | 0.5930 | 0.7701 |
|
| 263 |
+
| No log | 5.3671 | 424 | 0.5959 | 0.5097 | 0.5959 | 0.7720 |
|
| 264 |
+
| No log | 5.3924 | 426 | 0.5906 | 0.5633 | 0.5906 | 0.7685 |
|
| 265 |
+
| No log | 5.4177 | 428 | 0.6191 | 0.5111 | 0.6191 | 0.7868 |
|
| 266 |
+
| No log | 5.4430 | 430 | 0.6444 | 0.4810 | 0.6444 | 0.8028 |
|
| 267 |
+
| No log | 5.4684 | 432 | 0.6630 | 0.4375 | 0.6630 | 0.8142 |
|
| 268 |
+
| No log | 5.4937 | 434 | 0.6562 | 0.4625 | 0.6562 | 0.8101 |
|
| 269 |
+
| No log | 5.5190 | 436 | 0.6228 | 0.4833 | 0.6228 | 0.7892 |
|
| 270 |
+
| No log | 5.5443 | 438 | 0.5701 | 0.5382 | 0.5701 | 0.7550 |
|
| 271 |
+
| No log | 5.5696 | 440 | 0.5881 | 0.4384 | 0.5881 | 0.7669 |
|
| 272 |
+
| No log | 5.5949 | 442 | 0.6408 | 0.4442 | 0.6408 | 0.8005 |
|
| 273 |
+
| No log | 5.6203 | 444 | 0.6268 | 0.4747 | 0.6268 | 0.7917 |
|
| 274 |
+
| No log | 5.6456 | 446 | 0.5914 | 0.5323 | 0.5914 | 0.7690 |
|
| 275 |
+
| No log | 5.6709 | 448 | 0.6275 | 0.5661 | 0.6275 | 0.7921 |
|
| 276 |
+
| No log | 5.6962 | 450 | 0.6294 | 0.5600 | 0.6294 | 0.7934 |
|
| 277 |
+
| No log | 5.7215 | 452 | 0.5861 | 0.5774 | 0.5861 | 0.7656 |
|
| 278 |
+
| No log | 5.7468 | 454 | 0.5718 | 0.5156 | 0.5718 | 0.7562 |
|
| 279 |
+
| No log | 5.7722 | 456 | 0.5758 | 0.4657 | 0.5758 | 0.7588 |
|
| 280 |
+
| No log | 5.7975 | 458 | 0.5800 | 0.4573 | 0.5800 | 0.7616 |
|
| 281 |
+
| No log | 5.8228 | 460 | 0.6208 | 0.4773 | 0.6208 | 0.7879 |
|
| 282 |
+
| No log | 5.8481 | 462 | 0.6354 | 0.4564 | 0.6354 | 0.7971 |
|
| 283 |
+
| No log | 5.8734 | 464 | 0.6435 | 0.4393 | 0.6435 | 0.8022 |
|
| 284 |
+
| No log | 5.8987 | 466 | 0.6906 | 0.4237 | 0.6906 | 0.8310 |
|
| 285 |
+
| No log | 5.9241 | 468 | 0.7598 | 0.4148 | 0.7598 | 0.8717 |
|
| 286 |
+
| No log | 5.9494 | 470 | 0.7457 | 0.4320 | 0.7457 | 0.8635 |
|
| 287 |
+
| No log | 5.9747 | 472 | 0.7141 | 0.4559 | 0.7141 | 0.8450 |
|
| 288 |
+
| No log | 6.0 | 474 | 0.6083 | 0.4745 | 0.6083 | 0.7799 |
|
| 289 |
+
| No log | 6.0253 | 476 | 0.6253 | 0.5565 | 0.6253 | 0.7908 |
|
| 290 |
+
| No log | 6.0506 | 478 | 0.6563 | 0.5719 | 0.6563 | 0.8101 |
|
| 291 |
+
| No log | 6.0759 | 480 | 0.6364 | 0.5869 | 0.6364 | 0.7978 |
|
| 292 |
+
| No log | 6.1013 | 482 | 0.6279 | 0.4892 | 0.6279 | 0.7924 |
|
| 293 |
+
| No log | 6.1266 | 484 | 0.6431 | 0.4654 | 0.6431 | 0.8019 |
|
| 294 |
+
| No log | 6.1519 | 486 | 0.6719 | 0.4531 | 0.6719 | 0.8197 |
|
| 295 |
+
| No log | 6.1772 | 488 | 0.6527 | 0.4728 | 0.6527 | 0.8079 |
|
| 296 |
+
| No log | 6.2025 | 490 | 0.6285 | 0.4765 | 0.6285 | 0.7928 |
|
| 297 |
+
| No log | 6.2278 | 492 | 0.6124 | 0.4556 | 0.6124 | 0.7826 |
|
| 298 |
+
| No log | 6.2532 | 494 | 0.6047 | 0.4431 | 0.6047 | 0.7776 |
|
| 299 |
+
| No log | 6.2785 | 496 | 0.6152 | 0.4866 | 0.6152 | 0.7844 |
|
| 300 |
+
| No log | 6.3038 | 498 | 0.6106 | 0.4786 | 0.6106 | 0.7814 |
|
| 301 |
+
| 0.3637 | 6.3291 | 500 | 0.5979 | 0.4868 | 0.5979 | 0.7732 |
|
| 302 |
+
| 0.3637 | 6.3544 | 502 | 0.5981 | 0.5076 | 0.5981 | 0.7734 |
|
| 303 |
+
| 0.3637 | 6.3797 | 504 | 0.5825 | 0.4899 | 0.5825 | 0.7632 |
|
| 304 |
+
| 0.3637 | 6.4051 | 506 | 0.5805 | 0.4886 | 0.5805 | 0.7619 |
|
| 305 |
+
| 0.3637 | 6.4304 | 508 | 0.5750 | 0.5160 | 0.5750 | 0.7583 |
|
| 306 |
+
| 0.3637 | 6.4557 | 510 | 0.5761 | 0.5198 | 0.5761 | 0.7590 |
|
| 307 |
+
| 0.3637 | 6.4810 | 512 | 0.6370 | 0.4833 | 0.6370 | 0.7981 |
|
| 308 |
+
| 0.3637 | 6.5063 | 514 | 0.7102 | 0.4531 | 0.7102 | 0.8427 |
|
| 309 |
+
| 0.3637 | 6.5316 | 516 | 0.6860 | 0.4538 | 0.6860 | 0.8282 |
|
| 310 |
+
| 0.3637 | 6.5570 | 518 | 0.5986 | 0.3838 | 0.5986 | 0.7737 |
|
| 311 |
+
| 0.3637 | 6.5823 | 520 | 0.5737 | 0.3877 | 0.5737 | 0.7574 |
|
| 312 |
+
|
| 313 |
+
|
| 314 |
+
### Framework versions
|
| 315 |
+
|
| 316 |
+
- Transformers 4.44.2
|
| 317 |
+
- Pytorch 2.4.0+cu118
|
| 318 |
+
- Datasets 2.21.0
|
| 319 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 64000
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b0a9bad18a6395fe1b82fc1d01ff19228530ae3fedcba9ab403335f2265b807
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d550aded45761c9d60e8ae80f3f2125eb69e62797959cbd76058f91ea418fd28
|
| 3 |
+
size 5240
|