Training in progress, step 500
Browse files- README.md +315 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k2_task7_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 |
+
# ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k2_task7_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: 0.5778
|
| 19 |
+
- Qwk: 0.4752
|
| 20 |
+
- Mse: 0.5778
|
| 21 |
+
- Rmse: 0.7602
|
| 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 | 0.1818 | 2 | 2.5335 | -0.0262 | 2.5335 | 1.5917 |
|
| 53 |
+
| No log | 0.3636 | 4 | 1.2966 | 0.1565 | 1.2966 | 1.1387 |
|
| 54 |
+
| No log | 0.5455 | 6 | 1.0020 | -0.0672 | 1.0020 | 1.0010 |
|
| 55 |
+
| No log | 0.7273 | 8 | 0.8405 | 0.2866 | 0.8405 | 0.9168 |
|
| 56 |
+
| No log | 0.9091 | 10 | 0.7769 | 0.1541 | 0.7769 | 0.8814 |
|
| 57 |
+
| No log | 1.0909 | 12 | 0.7588 | 0.1714 | 0.7588 | 0.8711 |
|
| 58 |
+
| No log | 1.2727 | 14 | 0.7092 | 0.3123 | 0.7092 | 0.8421 |
|
| 59 |
+
| No log | 1.4545 | 16 | 0.7211 | 0.4148 | 0.7211 | 0.8492 |
|
| 60 |
+
| No log | 1.6364 | 18 | 0.7023 | 0.1633 | 0.7023 | 0.8380 |
|
| 61 |
+
| No log | 1.8182 | 20 | 0.9613 | 0.2356 | 0.9613 | 0.9805 |
|
| 62 |
+
| No log | 2.0 | 22 | 1.0066 | 0.1618 | 1.0066 | 1.0033 |
|
| 63 |
+
| No log | 2.1818 | 24 | 0.7566 | 0.1981 | 0.7566 | 0.8698 |
|
| 64 |
+
| No log | 2.3636 | 26 | 0.8663 | 0.2843 | 0.8663 | 0.9308 |
|
| 65 |
+
| No log | 2.5455 | 28 | 0.9408 | 0.2297 | 0.9408 | 0.9699 |
|
| 66 |
+
| No log | 2.7273 | 30 | 1.0010 | 0.2756 | 1.0010 | 1.0005 |
|
| 67 |
+
| No log | 2.9091 | 32 | 0.8984 | 0.2923 | 0.8984 | 0.9479 |
|
| 68 |
+
| No log | 3.0909 | 34 | 0.6978 | 0.1903 | 0.6978 | 0.8353 |
|
| 69 |
+
| No log | 3.2727 | 36 | 0.7884 | 0.1315 | 0.7884 | 0.8879 |
|
| 70 |
+
| No log | 3.4545 | 38 | 0.7767 | 0.2118 | 0.7767 | 0.8813 |
|
| 71 |
+
| No log | 3.6364 | 40 | 0.7280 | 0.1277 | 0.7280 | 0.8532 |
|
| 72 |
+
| No log | 3.8182 | 42 | 0.7453 | 0.1922 | 0.7453 | 0.8633 |
|
| 73 |
+
| No log | 4.0 | 44 | 0.7792 | 0.2027 | 0.7792 | 0.8827 |
|
| 74 |
+
| No log | 4.1818 | 46 | 0.8642 | 0.2632 | 0.8642 | 0.9296 |
|
| 75 |
+
| No log | 4.3636 | 48 | 0.8828 | 0.2244 | 0.8828 | 0.9396 |
|
| 76 |
+
| No log | 4.5455 | 50 | 0.8248 | 0.3032 | 0.8248 | 0.9082 |
|
| 77 |
+
| No log | 4.7273 | 52 | 0.6979 | 0.2181 | 0.6979 | 0.8354 |
|
| 78 |
+
| No log | 4.9091 | 54 | 0.8150 | 0.0913 | 0.8150 | 0.9028 |
|
| 79 |
+
| No log | 5.0909 | 56 | 1.1874 | 0.1508 | 1.1874 | 1.0897 |
|
| 80 |
+
| No log | 5.2727 | 58 | 1.3193 | 0.0103 | 1.3193 | 1.1486 |
|
| 81 |
+
| No log | 5.4545 | 60 | 1.1379 | 0.1775 | 1.1379 | 1.0667 |
|
| 82 |
+
| No log | 5.6364 | 62 | 0.8591 | 0.1697 | 0.8591 | 0.9269 |
|
| 83 |
+
| No log | 5.8182 | 64 | 0.7335 | 0.1539 | 0.7335 | 0.8564 |
|
| 84 |
+
| No log | 6.0 | 66 | 0.7391 | 0.2063 | 0.7391 | 0.8597 |
|
| 85 |
+
| No log | 6.1818 | 68 | 0.8225 | 0.2692 | 0.8225 | 0.9069 |
|
| 86 |
+
| No log | 6.3636 | 70 | 0.8297 | 0.2692 | 0.8297 | 0.9109 |
|
| 87 |
+
| No log | 6.5455 | 72 | 0.7806 | 0.2754 | 0.7806 | 0.8835 |
|
| 88 |
+
| No log | 6.7273 | 74 | 0.7720 | 0.2817 | 0.7720 | 0.8786 |
|
| 89 |
+
| No log | 6.9091 | 76 | 0.7118 | 0.3976 | 0.7118 | 0.8437 |
|
| 90 |
+
| No log | 7.0909 | 78 | 0.6926 | 0.2447 | 0.6926 | 0.8322 |
|
| 91 |
+
| No log | 7.2727 | 80 | 0.7159 | 0.3089 | 0.7159 | 0.8461 |
|
| 92 |
+
| No log | 7.4545 | 82 | 0.6923 | 0.3070 | 0.6923 | 0.8320 |
|
| 93 |
+
| No log | 7.6364 | 84 | 0.6890 | 0.3599 | 0.6890 | 0.8301 |
|
| 94 |
+
| No log | 7.8182 | 86 | 0.7276 | 0.3524 | 0.7276 | 0.8530 |
|
| 95 |
+
| No log | 8.0 | 88 | 0.7597 | 0.3811 | 0.7597 | 0.8716 |
|
| 96 |
+
| No log | 8.1818 | 90 | 0.7899 | 0.3213 | 0.7899 | 0.8888 |
|
| 97 |
+
| No log | 8.3636 | 92 | 0.8042 | 0.2568 | 0.8042 | 0.8968 |
|
| 98 |
+
| No log | 8.5455 | 94 | 0.8000 | 0.3816 | 0.8000 | 0.8944 |
|
| 99 |
+
| No log | 8.7273 | 96 | 0.8682 | 0.3802 | 0.8682 | 0.9318 |
|
| 100 |
+
| No log | 8.9091 | 98 | 0.8170 | 0.4522 | 0.8170 | 0.9039 |
|
| 101 |
+
| No log | 9.0909 | 100 | 0.6861 | 0.5037 | 0.6861 | 0.8283 |
|
| 102 |
+
| No log | 9.2727 | 102 | 0.7270 | 0.3962 | 0.7270 | 0.8527 |
|
| 103 |
+
| No log | 9.4545 | 104 | 0.8036 | 0.3381 | 0.8036 | 0.8964 |
|
| 104 |
+
| No log | 9.6364 | 106 | 0.7724 | 0.3381 | 0.7724 | 0.8789 |
|
| 105 |
+
| No log | 9.8182 | 108 | 0.6827 | 0.4429 | 0.6827 | 0.8262 |
|
| 106 |
+
| No log | 10.0 | 110 | 0.6178 | 0.5750 | 0.6178 | 0.7860 |
|
| 107 |
+
| No log | 10.1818 | 112 | 0.7026 | 0.3971 | 0.7026 | 0.8382 |
|
| 108 |
+
| No log | 10.3636 | 114 | 0.7962 | 0.3251 | 0.7962 | 0.8923 |
|
| 109 |
+
| No log | 10.5455 | 116 | 0.7449 | 0.3425 | 0.7449 | 0.8631 |
|
| 110 |
+
| No log | 10.7273 | 118 | 0.6792 | 0.4568 | 0.6792 | 0.8241 |
|
| 111 |
+
| No log | 10.9091 | 120 | 0.6376 | 0.4550 | 0.6376 | 0.7985 |
|
| 112 |
+
| No log | 11.0909 | 122 | 0.6506 | 0.4309 | 0.6506 | 0.8066 |
|
| 113 |
+
| No log | 11.2727 | 124 | 0.6455 | 0.4288 | 0.6455 | 0.8034 |
|
| 114 |
+
| No log | 11.4545 | 126 | 0.6411 | 0.5168 | 0.6411 | 0.8007 |
|
| 115 |
+
| No log | 11.6364 | 128 | 0.6402 | 0.4980 | 0.6402 | 0.8001 |
|
| 116 |
+
| No log | 11.8182 | 130 | 0.6335 | 0.4848 | 0.6335 | 0.7959 |
|
| 117 |
+
| No log | 12.0 | 132 | 0.6408 | 0.4382 | 0.6408 | 0.8005 |
|
| 118 |
+
| No log | 12.1818 | 134 | 0.6588 | 0.4438 | 0.6588 | 0.8117 |
|
| 119 |
+
| No log | 12.3636 | 136 | 0.6797 | 0.4059 | 0.6797 | 0.8244 |
|
| 120 |
+
| No log | 12.5455 | 138 | 0.6905 | 0.4575 | 0.6905 | 0.8310 |
|
| 121 |
+
| No log | 12.7273 | 140 | 0.7020 | 0.4114 | 0.7020 | 0.8379 |
|
| 122 |
+
| No log | 12.9091 | 142 | 0.7072 | 0.4493 | 0.7072 | 0.8410 |
|
| 123 |
+
| No log | 13.0909 | 144 | 0.7037 | 0.4534 | 0.7037 | 0.8388 |
|
| 124 |
+
| No log | 13.2727 | 146 | 0.6884 | 0.4206 | 0.6884 | 0.8297 |
|
| 125 |
+
| No log | 13.4545 | 148 | 0.6778 | 0.3100 | 0.6778 | 0.8233 |
|
| 126 |
+
| No log | 13.6364 | 150 | 0.6738 | 0.3308 | 0.6738 | 0.8209 |
|
| 127 |
+
| No log | 13.8182 | 152 | 0.6605 | 0.3391 | 0.6605 | 0.8127 |
|
| 128 |
+
| No log | 14.0 | 154 | 0.6489 | 0.3762 | 0.6489 | 0.8056 |
|
| 129 |
+
| No log | 14.1818 | 156 | 0.6330 | 0.4082 | 0.6330 | 0.7956 |
|
| 130 |
+
| No log | 14.3636 | 158 | 0.6439 | 0.4497 | 0.6439 | 0.8024 |
|
| 131 |
+
| No log | 14.5455 | 160 | 0.6555 | 0.3972 | 0.6555 | 0.8096 |
|
| 132 |
+
| No log | 14.7273 | 162 | 0.6415 | 0.3625 | 0.6415 | 0.8009 |
|
| 133 |
+
| No log | 14.9091 | 164 | 0.6530 | 0.4847 | 0.6530 | 0.8081 |
|
| 134 |
+
| No log | 15.0909 | 166 | 0.7184 | 0.4423 | 0.7184 | 0.8476 |
|
| 135 |
+
| No log | 15.2727 | 168 | 0.6777 | 0.4336 | 0.6777 | 0.8232 |
|
| 136 |
+
| No log | 15.4545 | 170 | 0.6756 | 0.4413 | 0.6756 | 0.8220 |
|
| 137 |
+
| No log | 15.6364 | 172 | 0.6696 | 0.3891 | 0.6696 | 0.8183 |
|
| 138 |
+
| No log | 15.8182 | 174 | 0.6011 | 0.4914 | 0.6011 | 0.7753 |
|
| 139 |
+
| No log | 16.0 | 176 | 0.5945 | 0.5044 | 0.5945 | 0.7710 |
|
| 140 |
+
| No log | 16.1818 | 178 | 0.6088 | 0.4850 | 0.6088 | 0.7802 |
|
| 141 |
+
| No log | 16.3636 | 180 | 0.5715 | 0.5248 | 0.5715 | 0.7559 |
|
| 142 |
+
| No log | 16.5455 | 182 | 0.5573 | 0.5143 | 0.5573 | 0.7465 |
|
| 143 |
+
| No log | 16.7273 | 184 | 0.5907 | 0.4635 | 0.5907 | 0.7686 |
|
| 144 |
+
| No log | 16.9091 | 186 | 0.6050 | 0.4329 | 0.6050 | 0.7778 |
|
| 145 |
+
| No log | 17.0909 | 188 | 0.6113 | 0.4308 | 0.6113 | 0.7819 |
|
| 146 |
+
| No log | 17.2727 | 190 | 0.6140 | 0.5323 | 0.6140 | 0.7836 |
|
| 147 |
+
| No log | 17.4545 | 192 | 0.6063 | 0.5396 | 0.6063 | 0.7787 |
|
| 148 |
+
| No log | 17.6364 | 194 | 0.5975 | 0.5252 | 0.5975 | 0.7730 |
|
| 149 |
+
| No log | 17.8182 | 196 | 0.6013 | 0.5405 | 0.6013 | 0.7754 |
|
| 150 |
+
| No log | 18.0 | 198 | 0.6100 | 0.5421 | 0.6100 | 0.7810 |
|
| 151 |
+
| No log | 18.1818 | 200 | 0.6672 | 0.5471 | 0.6672 | 0.8168 |
|
| 152 |
+
| No log | 18.3636 | 202 | 0.7221 | 0.4551 | 0.7221 | 0.8497 |
|
| 153 |
+
| No log | 18.5455 | 204 | 0.7406 | 0.4821 | 0.7406 | 0.8606 |
|
| 154 |
+
| No log | 18.7273 | 206 | 0.6534 | 0.5144 | 0.6534 | 0.8084 |
|
| 155 |
+
| No log | 18.9091 | 208 | 0.5831 | 0.5252 | 0.5831 | 0.7636 |
|
| 156 |
+
| No log | 19.0909 | 210 | 0.5514 | 0.5413 | 0.5514 | 0.7425 |
|
| 157 |
+
| No log | 19.2727 | 212 | 0.5337 | 0.5436 | 0.5337 | 0.7306 |
|
| 158 |
+
| No log | 19.4545 | 214 | 0.5217 | 0.5368 | 0.5217 | 0.7223 |
|
| 159 |
+
| No log | 19.6364 | 216 | 0.5172 | 0.5580 | 0.5172 | 0.7192 |
|
| 160 |
+
| No log | 19.8182 | 218 | 0.5141 | 0.5956 | 0.5141 | 0.7170 |
|
| 161 |
+
| No log | 20.0 | 220 | 0.5172 | 0.5956 | 0.5172 | 0.7191 |
|
| 162 |
+
| No log | 20.1818 | 222 | 0.5236 | 0.5768 | 0.5236 | 0.7236 |
|
| 163 |
+
| No log | 20.3636 | 224 | 0.5456 | 0.5549 | 0.5456 | 0.7386 |
|
| 164 |
+
| No log | 20.5455 | 226 | 0.5569 | 0.5662 | 0.5569 | 0.7463 |
|
| 165 |
+
| No log | 20.7273 | 228 | 0.5460 | 0.5549 | 0.5460 | 0.7389 |
|
| 166 |
+
| No log | 20.9091 | 230 | 0.5460 | 0.5505 | 0.5460 | 0.7389 |
|
| 167 |
+
| No log | 21.0909 | 232 | 0.5614 | 0.5022 | 0.5614 | 0.7493 |
|
| 168 |
+
| No log | 21.2727 | 234 | 0.5777 | 0.5095 | 0.5777 | 0.7601 |
|
| 169 |
+
| No log | 21.4545 | 236 | 0.5768 | 0.5344 | 0.5768 | 0.7595 |
|
| 170 |
+
| No log | 21.6364 | 238 | 0.5800 | 0.5268 | 0.5800 | 0.7616 |
|
| 171 |
+
| No log | 21.8182 | 240 | 0.5777 | 0.5446 | 0.5777 | 0.7601 |
|
| 172 |
+
| No log | 22.0 | 242 | 0.5877 | 0.5672 | 0.5877 | 0.7666 |
|
| 173 |
+
| No log | 22.1818 | 244 | 0.6134 | 0.4425 | 0.6134 | 0.7832 |
|
| 174 |
+
| No log | 22.3636 | 246 | 0.6020 | 0.5160 | 0.6020 | 0.7759 |
|
| 175 |
+
| No log | 22.5455 | 248 | 0.5944 | 0.5143 | 0.5944 | 0.7710 |
|
| 176 |
+
| No log | 22.7273 | 250 | 0.6286 | 0.4504 | 0.6286 | 0.7929 |
|
| 177 |
+
| No log | 22.9091 | 252 | 0.6855 | 0.4473 | 0.6855 | 0.8280 |
|
| 178 |
+
| No log | 23.0909 | 254 | 0.6930 | 0.4212 | 0.6930 | 0.8325 |
|
| 179 |
+
| No log | 23.2727 | 256 | 0.6746 | 0.4212 | 0.6746 | 0.8214 |
|
| 180 |
+
| No log | 23.4545 | 258 | 0.6650 | 0.4637 | 0.6650 | 0.8155 |
|
| 181 |
+
| No log | 23.6364 | 260 | 0.6433 | 0.4908 | 0.6433 | 0.8020 |
|
| 182 |
+
| No log | 23.8182 | 262 | 0.6151 | 0.4276 | 0.6151 | 0.7843 |
|
| 183 |
+
| No log | 24.0 | 264 | 0.6563 | 0.4411 | 0.6563 | 0.8101 |
|
| 184 |
+
| No log | 24.1818 | 266 | 0.6477 | 0.4821 | 0.6477 | 0.8048 |
|
| 185 |
+
| No log | 24.3636 | 268 | 0.6346 | 0.3810 | 0.6346 | 0.7966 |
|
| 186 |
+
| No log | 24.5455 | 270 | 0.6485 | 0.4253 | 0.6485 | 0.8053 |
|
| 187 |
+
| No log | 24.7273 | 272 | 0.6819 | 0.4234 | 0.6819 | 0.8258 |
|
| 188 |
+
| No log | 24.9091 | 274 | 0.6544 | 0.4147 | 0.6544 | 0.8089 |
|
| 189 |
+
| No log | 25.0909 | 276 | 0.6203 | 0.4788 | 0.6203 | 0.7876 |
|
| 190 |
+
| No log | 25.2727 | 278 | 0.6113 | 0.4788 | 0.6113 | 0.7819 |
|
| 191 |
+
| No log | 25.4545 | 280 | 0.6291 | 0.4569 | 0.6291 | 0.7932 |
|
| 192 |
+
| No log | 25.6364 | 282 | 0.6518 | 0.4707 | 0.6518 | 0.8074 |
|
| 193 |
+
| No log | 25.8182 | 284 | 0.6789 | 0.4020 | 0.6789 | 0.8240 |
|
| 194 |
+
| No log | 26.0 | 286 | 0.7247 | 0.3844 | 0.7247 | 0.8513 |
|
| 195 |
+
| No log | 26.1818 | 288 | 0.7122 | 0.3519 | 0.7122 | 0.8439 |
|
| 196 |
+
| No log | 26.3636 | 290 | 0.6364 | 0.4420 | 0.6364 | 0.7978 |
|
| 197 |
+
| No log | 26.5455 | 292 | 0.5992 | 0.5344 | 0.5992 | 0.7741 |
|
| 198 |
+
| No log | 26.7273 | 294 | 0.5874 | 0.5344 | 0.5874 | 0.7664 |
|
| 199 |
+
| No log | 26.9091 | 296 | 0.5771 | 0.5344 | 0.5771 | 0.7597 |
|
| 200 |
+
| No log | 27.0909 | 298 | 0.5793 | 0.5344 | 0.5793 | 0.7611 |
|
| 201 |
+
| No log | 27.2727 | 300 | 0.5873 | 0.4919 | 0.5873 | 0.7664 |
|
| 202 |
+
| No log | 27.4545 | 302 | 0.5826 | 0.5159 | 0.5826 | 0.7633 |
|
| 203 |
+
| No log | 27.6364 | 304 | 0.5978 | 0.4434 | 0.5978 | 0.7732 |
|
| 204 |
+
| No log | 27.8182 | 306 | 0.5706 | 0.5095 | 0.5706 | 0.7554 |
|
| 205 |
+
| No log | 28.0 | 308 | 0.5593 | 0.5344 | 0.5593 | 0.7479 |
|
| 206 |
+
| No log | 28.1818 | 310 | 0.5520 | 0.5584 | 0.5520 | 0.7430 |
|
| 207 |
+
| No log | 28.3636 | 312 | 0.5502 | 0.5815 | 0.5502 | 0.7417 |
|
| 208 |
+
| No log | 28.5455 | 314 | 0.5490 | 0.5580 | 0.5490 | 0.7409 |
|
| 209 |
+
| No log | 28.7273 | 316 | 0.5482 | 0.5736 | 0.5482 | 0.7404 |
|
| 210 |
+
| No log | 28.9091 | 318 | 0.5383 | 0.5734 | 0.5383 | 0.7337 |
|
| 211 |
+
| No log | 29.0909 | 320 | 0.5611 | 0.4660 | 0.5611 | 0.7491 |
|
| 212 |
+
| No log | 29.2727 | 322 | 0.6592 | 0.4165 | 0.6592 | 0.8119 |
|
| 213 |
+
| No log | 29.4545 | 324 | 0.7107 | 0.3973 | 0.7107 | 0.8430 |
|
| 214 |
+
| No log | 29.6364 | 326 | 0.6897 | 0.3934 | 0.6897 | 0.8305 |
|
| 215 |
+
| No log | 29.8182 | 328 | 0.6040 | 0.4945 | 0.6040 | 0.7772 |
|
| 216 |
+
| No log | 30.0 | 330 | 0.5510 | 0.5022 | 0.5510 | 0.7423 |
|
| 217 |
+
| No log | 30.1818 | 332 | 0.5964 | 0.4575 | 0.5964 | 0.7723 |
|
| 218 |
+
| No log | 30.3636 | 334 | 0.6158 | 0.4807 | 0.6158 | 0.7847 |
|
| 219 |
+
| No log | 30.5455 | 336 | 0.5607 | 0.5861 | 0.5607 | 0.7488 |
|
| 220 |
+
| No log | 30.7273 | 338 | 0.5555 | 0.5584 | 0.5555 | 0.7453 |
|
| 221 |
+
| No log | 30.9091 | 340 | 0.6418 | 0.3936 | 0.6418 | 0.8011 |
|
| 222 |
+
| No log | 31.0909 | 342 | 0.6715 | 0.4144 | 0.6715 | 0.8195 |
|
| 223 |
+
| No log | 31.2727 | 344 | 0.6102 | 0.4724 | 0.6102 | 0.7811 |
|
| 224 |
+
| No log | 31.4545 | 346 | 0.5373 | 0.5734 | 0.5373 | 0.7330 |
|
| 225 |
+
| No log | 31.6364 | 348 | 0.5660 | 0.5554 | 0.5660 | 0.7523 |
|
| 226 |
+
| No log | 31.8182 | 350 | 0.6033 | 0.5090 | 0.6033 | 0.7767 |
|
| 227 |
+
| No log | 32.0 | 352 | 0.5994 | 0.5090 | 0.5994 | 0.7742 |
|
| 228 |
+
| No log | 32.1818 | 354 | 0.5779 | 0.5127 | 0.5779 | 0.7602 |
|
| 229 |
+
| No log | 32.3636 | 356 | 0.5556 | 0.5178 | 0.5556 | 0.7454 |
|
| 230 |
+
| No log | 32.5455 | 358 | 0.5551 | 0.5846 | 0.5551 | 0.7451 |
|
| 231 |
+
| No log | 32.7273 | 360 | 0.5669 | 0.5250 | 0.5669 | 0.7529 |
|
| 232 |
+
| No log | 32.9091 | 362 | 0.5605 | 0.5584 | 0.5605 | 0.7487 |
|
| 233 |
+
| No log | 33.0909 | 364 | 0.5635 | 0.5304 | 0.5635 | 0.7506 |
|
| 234 |
+
| No log | 33.2727 | 366 | 0.5732 | 0.5061 | 0.5732 | 0.7571 |
|
| 235 |
+
| No log | 33.4545 | 368 | 0.5742 | 0.4809 | 0.5742 | 0.7578 |
|
| 236 |
+
| No log | 33.6364 | 370 | 0.5787 | 0.5268 | 0.5787 | 0.7607 |
|
| 237 |
+
| No log | 33.8182 | 372 | 0.5798 | 0.5323 | 0.5798 | 0.7614 |
|
| 238 |
+
| No log | 34.0 | 374 | 0.5664 | 0.5798 | 0.5664 | 0.7526 |
|
| 239 |
+
| No log | 34.1818 | 376 | 0.5535 | 0.6371 | 0.5535 | 0.7440 |
|
| 240 |
+
| No log | 34.3636 | 378 | 0.5438 | 0.5846 | 0.5438 | 0.7374 |
|
| 241 |
+
| No log | 34.5455 | 380 | 0.5287 | 0.5379 | 0.5287 | 0.7271 |
|
| 242 |
+
| No log | 34.7273 | 382 | 0.5260 | 0.5765 | 0.5260 | 0.7252 |
|
| 243 |
+
| No log | 34.9091 | 384 | 0.5404 | 0.4964 | 0.5404 | 0.7351 |
|
| 244 |
+
| No log | 35.0909 | 386 | 0.5708 | 0.5098 | 0.5708 | 0.7555 |
|
| 245 |
+
| No log | 35.2727 | 388 | 0.6577 | 0.5227 | 0.6577 | 0.8110 |
|
| 246 |
+
| No log | 35.4545 | 390 | 0.7531 | 0.4650 | 0.7531 | 0.8678 |
|
| 247 |
+
| No log | 35.6364 | 392 | 0.8333 | 0.3849 | 0.8333 | 0.9129 |
|
| 248 |
+
| No log | 35.8182 | 394 | 0.7658 | 0.3719 | 0.7658 | 0.8751 |
|
| 249 |
+
| No log | 36.0 | 396 | 0.6448 | 0.4430 | 0.6448 | 0.8030 |
|
| 250 |
+
| No log | 36.1818 | 398 | 0.5464 | 0.5250 | 0.5464 | 0.7392 |
|
| 251 |
+
| No log | 36.3636 | 400 | 0.5436 | 0.5152 | 0.5436 | 0.7373 |
|
| 252 |
+
| No log | 36.5455 | 402 | 0.5871 | 0.5781 | 0.5871 | 0.7662 |
|
| 253 |
+
| No log | 36.7273 | 404 | 0.5909 | 0.5841 | 0.5909 | 0.7687 |
|
| 254 |
+
| No log | 36.9091 | 406 | 0.5594 | 0.6154 | 0.5594 | 0.7479 |
|
| 255 |
+
| No log | 37.0909 | 408 | 0.5499 | 0.5235 | 0.5499 | 0.7416 |
|
| 256 |
+
| No log | 37.2727 | 410 | 0.5757 | 0.5003 | 0.5757 | 0.7588 |
|
| 257 |
+
| No log | 37.4545 | 412 | 0.5985 | 0.4681 | 0.5985 | 0.7736 |
|
| 258 |
+
| No log | 37.6364 | 414 | 0.5782 | 0.5268 | 0.5782 | 0.7604 |
|
| 259 |
+
| No log | 37.8182 | 416 | 0.5688 | 0.5042 | 0.5688 | 0.7542 |
|
| 260 |
+
| No log | 38.0 | 418 | 0.5923 | 0.5571 | 0.5923 | 0.7696 |
|
| 261 |
+
| No log | 38.1818 | 420 | 0.5978 | 0.4821 | 0.5978 | 0.7732 |
|
| 262 |
+
| No log | 38.3636 | 422 | 0.5741 | 0.5861 | 0.5741 | 0.7577 |
|
| 263 |
+
| No log | 38.5455 | 424 | 0.5572 | 0.5672 | 0.5572 | 0.7465 |
|
| 264 |
+
| No log | 38.7273 | 426 | 0.5713 | 0.4934 | 0.5713 | 0.7558 |
|
| 265 |
+
| No log | 38.9091 | 428 | 0.6056 | 0.4883 | 0.6056 | 0.7782 |
|
| 266 |
+
| No log | 39.0909 | 430 | 0.6275 | 0.4007 | 0.6275 | 0.7921 |
|
| 267 |
+
| No log | 39.2727 | 432 | 0.6396 | 0.3544 | 0.6396 | 0.7997 |
|
| 268 |
+
| No log | 39.4545 | 434 | 0.6386 | 0.3737 | 0.6386 | 0.7991 |
|
| 269 |
+
| No log | 39.6364 | 436 | 0.6263 | 0.3894 | 0.6263 | 0.7914 |
|
| 270 |
+
| No log | 39.8182 | 438 | 0.6128 | 0.4267 | 0.6128 | 0.7828 |
|
| 271 |
+
| No log | 40.0 | 440 | 0.6088 | 0.4547 | 0.6088 | 0.7802 |
|
| 272 |
+
| No log | 40.1818 | 442 | 0.6054 | 0.4514 | 0.6054 | 0.7780 |
|
| 273 |
+
| No log | 40.3636 | 444 | 0.5885 | 0.5150 | 0.5885 | 0.7672 |
|
| 274 |
+
| No log | 40.5455 | 446 | 0.5814 | 0.5160 | 0.5814 | 0.7625 |
|
| 275 |
+
| No log | 40.7273 | 448 | 0.6040 | 0.4507 | 0.6040 | 0.7772 |
|
| 276 |
+
| No log | 40.9091 | 450 | 0.6169 | 0.4391 | 0.6169 | 0.7854 |
|
| 277 |
+
| No log | 41.0909 | 452 | 0.6197 | 0.4391 | 0.6197 | 0.7872 |
|
| 278 |
+
| No log | 41.2727 | 454 | 0.5961 | 0.4737 | 0.5961 | 0.7720 |
|
| 279 |
+
| No log | 41.4545 | 456 | 0.5749 | 0.5321 | 0.5749 | 0.7582 |
|
| 280 |
+
| No log | 41.6364 | 458 | 0.5848 | 0.5177 | 0.5848 | 0.7647 |
|
| 281 |
+
| No log | 41.8182 | 460 | 0.6276 | 0.4493 | 0.6276 | 0.7922 |
|
| 282 |
+
| No log | 42.0 | 462 | 0.6431 | 0.4182 | 0.6431 | 0.8019 |
|
| 283 |
+
| No log | 42.1818 | 464 | 0.6285 | 0.4182 | 0.6285 | 0.7928 |
|
| 284 |
+
| No log | 42.3636 | 466 | 0.6177 | 0.4768 | 0.6177 | 0.7859 |
|
| 285 |
+
| No log | 42.5455 | 468 | 0.6226 | 0.4953 | 0.6226 | 0.7891 |
|
| 286 |
+
| No log | 42.7273 | 470 | 0.6293 | 0.4701 | 0.6293 | 0.7933 |
|
| 287 |
+
| No log | 42.9091 | 472 | 0.6407 | 0.4543 | 0.6407 | 0.8005 |
|
| 288 |
+
| No log | 43.0909 | 474 | 0.6441 | 0.4819 | 0.6441 | 0.8026 |
|
| 289 |
+
| No log | 43.2727 | 476 | 0.6441 | 0.4819 | 0.6441 | 0.8026 |
|
| 290 |
+
| No log | 43.4545 | 478 | 0.6314 | 0.4819 | 0.6314 | 0.7946 |
|
| 291 |
+
| No log | 43.6364 | 480 | 0.6019 | 0.4984 | 0.6019 | 0.7758 |
|
| 292 |
+
| No log | 43.8182 | 482 | 0.5929 | 0.5003 | 0.5929 | 0.7700 |
|
| 293 |
+
| No log | 44.0 | 484 | 0.6044 | 0.4984 | 0.6044 | 0.7774 |
|
| 294 |
+
| No log | 44.1818 | 486 | 0.6208 | 0.4895 | 0.6208 | 0.7879 |
|
| 295 |
+
| No log | 44.3636 | 488 | 0.6150 | 0.4895 | 0.6150 | 0.7842 |
|
| 296 |
+
| No log | 44.5455 | 490 | 0.5894 | 0.5076 | 0.5894 | 0.7677 |
|
| 297 |
+
| No log | 44.7273 | 492 | 0.5763 | 0.5250 | 0.5763 | 0.7591 |
|
| 298 |
+
| No log | 44.9091 | 494 | 0.5718 | 0.5505 | 0.5718 | 0.7562 |
|
| 299 |
+
| No log | 45.0909 | 496 | 0.5719 | 0.5357 | 0.5719 | 0.7562 |
|
| 300 |
+
| No log | 45.2727 | 498 | 0.5719 | 0.5719 | 0.5719 | 0.7562 |
|
| 301 |
+
| 0.3032 | 45.4545 | 500 | 0.5802 | 0.5250 | 0.5802 | 0.7617 |
|
| 302 |
+
| 0.3032 | 45.6364 | 502 | 0.5837 | 0.5505 | 0.5837 | 0.7640 |
|
| 303 |
+
| 0.3032 | 45.8182 | 504 | 0.5878 | 0.4923 | 0.5878 | 0.7667 |
|
| 304 |
+
| 0.3032 | 46.0 | 506 | 0.6050 | 0.4315 | 0.6050 | 0.7778 |
|
| 305 |
+
| 0.3032 | 46.1818 | 508 | 0.6142 | 0.4355 | 0.6142 | 0.7837 |
|
| 306 |
+
| 0.3032 | 46.3636 | 510 | 0.6024 | 0.4499 | 0.6024 | 0.7761 |
|
| 307 |
+
| 0.3032 | 46.5455 | 512 | 0.5778 | 0.4752 | 0.5778 | 0.7602 |
|
| 308 |
+
|
| 309 |
+
|
| 310 |
+
### Framework versions
|
| 311 |
+
|
| 312 |
+
- Transformers 4.44.2
|
| 313 |
+
- Pytorch 2.4.0+cu118
|
| 314 |
+
- Datasets 2.21.0
|
| 315 |
+
- 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:ff87fc7a151efd6f15ebdaec88b57cbfc52962ca40a2f2bfdb453bddd63db97d
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddf113182f295068326fbe7a238dd68b207aa5803d4db53f75d06cb0bf892c9c
|
| 3 |
+
size 5304
|