Training in progress, step 500
Browse files- README.md +321 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k18_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_k18_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: 0.6184
|
| 19 |
+
- Qwk: 0.5294
|
| 20 |
+
- Mse: 0.6184
|
| 21 |
+
- Rmse: 0.7864
|
| 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 | 0.0211 | 2 | 4.1288 | -0.0315 | 4.1288 | 2.0319 |
|
| 53 |
+
| No log | 0.0421 | 4 | 2.5185 | 0.0426 | 2.5185 | 1.5870 |
|
| 54 |
+
| No log | 0.0632 | 6 | 1.4666 | 0.1104 | 1.4666 | 1.2110 |
|
| 55 |
+
| No log | 0.0842 | 8 | 1.0851 | -0.0178 | 1.0851 | 1.0417 |
|
| 56 |
+
| No log | 0.1053 | 10 | 0.8797 | 0.0974 | 0.8797 | 0.9379 |
|
| 57 |
+
| No log | 0.1263 | 12 | 0.9451 | 0.0093 | 0.9451 | 0.9722 |
|
| 58 |
+
| No log | 0.1474 | 14 | 1.4534 | 0.0302 | 1.4534 | 1.2056 |
|
| 59 |
+
| No log | 0.1684 | 16 | 2.0478 | 0.0673 | 2.0478 | 1.4310 |
|
| 60 |
+
| No log | 0.1895 | 18 | 1.7795 | 0.0425 | 1.7795 | 1.3340 |
|
| 61 |
+
| No log | 0.2105 | 20 | 1.2998 | 0.0208 | 1.2998 | 1.1401 |
|
| 62 |
+
| No log | 0.2316 | 22 | 0.9965 | 0.0836 | 0.9965 | 0.9983 |
|
| 63 |
+
| No log | 0.2526 | 24 | 0.9233 | 0.1067 | 0.9233 | 0.9609 |
|
| 64 |
+
| No log | 0.2737 | 26 | 0.9016 | 0.0955 | 0.9016 | 0.9495 |
|
| 65 |
+
| No log | 0.2947 | 28 | 0.7589 | 0.2702 | 0.7589 | 0.8711 |
|
| 66 |
+
| No log | 0.3158 | 30 | 0.7519 | 0.2637 | 0.7519 | 0.8671 |
|
| 67 |
+
| No log | 0.3368 | 32 | 0.8252 | 0.1152 | 0.8252 | 0.9084 |
|
| 68 |
+
| No log | 0.3579 | 34 | 0.8629 | 0.1225 | 0.8629 | 0.9289 |
|
| 69 |
+
| No log | 0.3789 | 36 | 0.7928 | 0.1505 | 0.7928 | 0.8904 |
|
| 70 |
+
| No log | 0.4 | 38 | 0.7374 | 0.2376 | 0.7374 | 0.8587 |
|
| 71 |
+
| No log | 0.4211 | 40 | 0.8696 | 0.0914 | 0.8696 | 0.9325 |
|
| 72 |
+
| No log | 0.4421 | 42 | 0.8435 | 0.1149 | 0.8435 | 0.9184 |
|
| 73 |
+
| No log | 0.4632 | 44 | 0.8571 | 0.1489 | 0.8571 | 0.9258 |
|
| 74 |
+
| No log | 0.4842 | 46 | 0.9362 | 0.0903 | 0.9362 | 0.9676 |
|
| 75 |
+
| No log | 0.5053 | 48 | 1.1060 | 0.0718 | 1.1060 | 1.0517 |
|
| 76 |
+
| No log | 0.5263 | 50 | 1.0754 | 0.0615 | 1.0754 | 1.0370 |
|
| 77 |
+
| No log | 0.5474 | 52 | 1.0345 | 0.0769 | 1.0345 | 1.0171 |
|
| 78 |
+
| No log | 0.5684 | 54 | 1.0350 | 0.0769 | 1.0350 | 1.0173 |
|
| 79 |
+
| No log | 0.5895 | 56 | 0.9969 | 0.1118 | 0.9969 | 0.9984 |
|
| 80 |
+
| No log | 0.6105 | 58 | 0.9859 | 0.1416 | 0.9859 | 0.9929 |
|
| 81 |
+
| No log | 0.6316 | 60 | 0.9304 | 0.1334 | 0.9304 | 0.9646 |
|
| 82 |
+
| No log | 0.6526 | 62 | 0.7553 | 0.2849 | 0.7553 | 0.8691 |
|
| 83 |
+
| No log | 0.6737 | 64 | 0.7851 | 0.1643 | 0.7851 | 0.8860 |
|
| 84 |
+
| No log | 0.6947 | 66 | 0.8097 | 0.1643 | 0.8097 | 0.8999 |
|
| 85 |
+
| No log | 0.7158 | 68 | 0.7818 | 0.1904 | 0.7818 | 0.8842 |
|
| 86 |
+
| No log | 0.7368 | 70 | 0.7878 | 0.2766 | 0.7878 | 0.8876 |
|
| 87 |
+
| No log | 0.7579 | 72 | 0.8239 | 0.2505 | 0.8239 | 0.9077 |
|
| 88 |
+
| No log | 0.7789 | 74 | 0.8717 | 0.1621 | 0.8717 | 0.9336 |
|
| 89 |
+
| No log | 0.8 | 76 | 0.7942 | 0.3226 | 0.7942 | 0.8912 |
|
| 90 |
+
| No log | 0.8211 | 78 | 0.7783 | 0.3385 | 0.7783 | 0.8822 |
|
| 91 |
+
| No log | 0.8421 | 80 | 0.7546 | 0.2920 | 0.7546 | 0.8687 |
|
| 92 |
+
| No log | 0.8632 | 82 | 0.7792 | 0.2545 | 0.7792 | 0.8827 |
|
| 93 |
+
| No log | 0.8842 | 84 | 0.7480 | 0.3243 | 0.7480 | 0.8649 |
|
| 94 |
+
| No log | 0.9053 | 86 | 0.7029 | 0.2658 | 0.7029 | 0.8384 |
|
| 95 |
+
| No log | 0.9263 | 88 | 0.7026 | 0.3783 | 0.7026 | 0.8382 |
|
| 96 |
+
| No log | 0.9474 | 90 | 0.6902 | 0.3564 | 0.6902 | 0.8308 |
|
| 97 |
+
| No log | 0.9684 | 92 | 0.6650 | 0.3636 | 0.6650 | 0.8155 |
|
| 98 |
+
| No log | 0.9895 | 94 | 0.7505 | 0.2769 | 0.7505 | 0.8663 |
|
| 99 |
+
| No log | 1.0105 | 96 | 0.9071 | 0.1912 | 0.9071 | 0.9524 |
|
| 100 |
+
| No log | 1.0316 | 98 | 0.8257 | 0.1937 | 0.8257 | 0.9087 |
|
| 101 |
+
| No log | 1.0526 | 100 | 0.6927 | 0.3466 | 0.6927 | 0.8323 |
|
| 102 |
+
| No log | 1.0737 | 102 | 0.6683 | 0.3612 | 0.6683 | 0.8175 |
|
| 103 |
+
| No log | 1.0947 | 104 | 0.7382 | 0.3380 | 0.7382 | 0.8592 |
|
| 104 |
+
| No log | 1.1158 | 106 | 0.9529 | 0.2659 | 0.9529 | 0.9762 |
|
| 105 |
+
| No log | 1.1368 | 108 | 0.9635 | 0.3044 | 0.9635 | 0.9816 |
|
| 106 |
+
| No log | 1.1579 | 110 | 0.7591 | 0.3529 | 0.7591 | 0.8713 |
|
| 107 |
+
| No log | 1.1789 | 112 | 0.6922 | 0.3792 | 0.6922 | 0.8320 |
|
| 108 |
+
| No log | 1.2 | 114 | 0.7296 | 0.3937 | 0.7296 | 0.8542 |
|
| 109 |
+
| No log | 1.2211 | 116 | 0.7899 | 0.3672 | 0.7899 | 0.8888 |
|
| 110 |
+
| No log | 1.2421 | 118 | 0.8106 | 0.3884 | 0.8106 | 0.9003 |
|
| 111 |
+
| No log | 1.2632 | 120 | 0.7301 | 0.4256 | 0.7301 | 0.8545 |
|
| 112 |
+
| No log | 1.2842 | 122 | 0.8867 | 0.4489 | 0.8867 | 0.9417 |
|
| 113 |
+
| No log | 1.3053 | 124 | 0.9356 | 0.4196 | 0.9356 | 0.9673 |
|
| 114 |
+
| No log | 1.3263 | 126 | 0.8363 | 0.4475 | 0.8363 | 0.9145 |
|
| 115 |
+
| No log | 1.3474 | 128 | 0.6997 | 0.3396 | 0.6997 | 0.8365 |
|
| 116 |
+
| No log | 1.3684 | 130 | 0.7186 | 0.3959 | 0.7186 | 0.8477 |
|
| 117 |
+
| No log | 1.3895 | 132 | 0.7385 | 0.3838 | 0.7385 | 0.8594 |
|
| 118 |
+
| No log | 1.4105 | 134 | 0.6888 | 0.4018 | 0.6888 | 0.8299 |
|
| 119 |
+
| No log | 1.4316 | 136 | 0.7473 | 0.4035 | 0.7473 | 0.8644 |
|
| 120 |
+
| No log | 1.4526 | 138 | 0.9286 | 0.3883 | 0.9286 | 0.9636 |
|
| 121 |
+
| No log | 1.4737 | 140 | 1.0840 | 0.2961 | 1.0840 | 1.0412 |
|
| 122 |
+
| No log | 1.4947 | 142 | 0.8336 | 0.3932 | 0.8336 | 0.9130 |
|
| 123 |
+
| No log | 1.5158 | 144 | 0.7058 | 0.4382 | 0.7058 | 0.8401 |
|
| 124 |
+
| No log | 1.5368 | 146 | 0.7232 | 0.4489 | 0.7232 | 0.8504 |
|
| 125 |
+
| No log | 1.5579 | 148 | 0.8145 | 0.3962 | 0.8145 | 0.9025 |
|
| 126 |
+
| No log | 1.5789 | 150 | 0.8053 | 0.4102 | 0.8053 | 0.8974 |
|
| 127 |
+
| No log | 1.6 | 152 | 0.7190 | 0.4421 | 0.7190 | 0.8479 |
|
| 128 |
+
| No log | 1.6211 | 154 | 0.7069 | 0.4567 | 0.7069 | 0.8408 |
|
| 129 |
+
| No log | 1.6421 | 156 | 0.7192 | 0.4628 | 0.7192 | 0.8481 |
|
| 130 |
+
| No log | 1.6632 | 158 | 0.9127 | 0.3297 | 0.9127 | 0.9554 |
|
| 131 |
+
| No log | 1.6842 | 160 | 1.3862 | 0.2134 | 1.3862 | 1.1774 |
|
| 132 |
+
| No log | 1.7053 | 162 | 1.4692 | 0.2036 | 1.4692 | 1.2121 |
|
| 133 |
+
| No log | 1.7263 | 164 | 1.0294 | 0.2771 | 1.0294 | 1.0146 |
|
| 134 |
+
| No log | 1.7474 | 166 | 0.6834 | 0.4687 | 0.6834 | 0.8267 |
|
| 135 |
+
| No log | 1.7684 | 168 | 0.6539 | 0.4906 | 0.6539 | 0.8086 |
|
| 136 |
+
| No log | 1.7895 | 170 | 0.6982 | 0.4477 | 0.6982 | 0.8356 |
|
| 137 |
+
| No log | 1.8105 | 172 | 0.7451 | 0.4087 | 0.7451 | 0.8632 |
|
| 138 |
+
| No log | 1.8316 | 174 | 0.8036 | 0.4019 | 0.8036 | 0.8965 |
|
| 139 |
+
| No log | 1.8526 | 176 | 0.8099 | 0.3935 | 0.8099 | 0.8999 |
|
| 140 |
+
| No log | 1.8737 | 178 | 0.8201 | 0.4115 | 0.8201 | 0.9056 |
|
| 141 |
+
| No log | 1.8947 | 180 | 0.8681 | 0.4417 | 0.8681 | 0.9317 |
|
| 142 |
+
| No log | 1.9158 | 182 | 0.8429 | 0.4423 | 0.8429 | 0.9181 |
|
| 143 |
+
| No log | 1.9368 | 184 | 0.7964 | 0.4683 | 0.7964 | 0.8924 |
|
| 144 |
+
| No log | 1.9579 | 186 | 0.7728 | 0.4223 | 0.7728 | 0.8791 |
|
| 145 |
+
| No log | 1.9789 | 188 | 0.8025 | 0.4409 | 0.8025 | 0.8958 |
|
| 146 |
+
| No log | 2.0 | 190 | 0.8573 | 0.4339 | 0.8573 | 0.9259 |
|
| 147 |
+
| No log | 2.0211 | 192 | 0.8898 | 0.4230 | 0.8898 | 0.9433 |
|
| 148 |
+
| No log | 2.0421 | 194 | 0.8453 | 0.4237 | 0.8453 | 0.9194 |
|
| 149 |
+
| No log | 2.0632 | 196 | 0.7927 | 0.4640 | 0.7927 | 0.8904 |
|
| 150 |
+
| No log | 2.0842 | 198 | 0.6814 | 0.4616 | 0.6814 | 0.8255 |
|
| 151 |
+
| No log | 2.1053 | 200 | 0.6805 | 0.3876 | 0.6805 | 0.8249 |
|
| 152 |
+
| No log | 2.1263 | 202 | 0.7932 | 0.4137 | 0.7932 | 0.8906 |
|
| 153 |
+
| No log | 2.1474 | 204 | 0.8210 | 0.3537 | 0.8210 | 0.9061 |
|
| 154 |
+
| No log | 2.1684 | 206 | 0.6529 | 0.4375 | 0.6529 | 0.8080 |
|
| 155 |
+
| No log | 2.1895 | 208 | 0.5770 | 0.4339 | 0.5770 | 0.7596 |
|
| 156 |
+
| No log | 2.2105 | 210 | 0.5688 | 0.4584 | 0.5688 | 0.7542 |
|
| 157 |
+
| No log | 2.2316 | 212 | 0.5937 | 0.4436 | 0.5937 | 0.7705 |
|
| 158 |
+
| No log | 2.2526 | 214 | 0.6245 | 0.4381 | 0.6245 | 0.7903 |
|
| 159 |
+
| No log | 2.2737 | 216 | 0.6395 | 0.4528 | 0.6395 | 0.7997 |
|
| 160 |
+
| No log | 2.2947 | 218 | 0.6386 | 0.4830 | 0.6386 | 0.7991 |
|
| 161 |
+
| No log | 2.3158 | 220 | 0.6937 | 0.4787 | 0.6937 | 0.8329 |
|
| 162 |
+
| No log | 2.3368 | 222 | 0.7709 | 0.4437 | 0.7709 | 0.8780 |
|
| 163 |
+
| No log | 2.3579 | 224 | 0.7213 | 0.3433 | 0.7213 | 0.8493 |
|
| 164 |
+
| No log | 2.3789 | 226 | 0.6798 | 0.3799 | 0.6798 | 0.8245 |
|
| 165 |
+
| No log | 2.4 | 228 | 0.6615 | 0.4124 | 0.6615 | 0.8133 |
|
| 166 |
+
| No log | 2.4211 | 230 | 0.6727 | 0.4200 | 0.6727 | 0.8202 |
|
| 167 |
+
| No log | 2.4421 | 232 | 0.7324 | 0.3683 | 0.7324 | 0.8558 |
|
| 168 |
+
| No log | 2.4632 | 234 | 0.6935 | 0.3867 | 0.6935 | 0.8327 |
|
| 169 |
+
| No log | 2.4842 | 236 | 0.6711 | 0.3579 | 0.6711 | 0.8192 |
|
| 170 |
+
| No log | 2.5053 | 238 | 0.6323 | 0.4102 | 0.6323 | 0.7952 |
|
| 171 |
+
| No log | 2.5263 | 240 | 0.6303 | 0.4339 | 0.6303 | 0.7939 |
|
| 172 |
+
| No log | 2.5474 | 242 | 0.6294 | 0.4273 | 0.6294 | 0.7933 |
|
| 173 |
+
| No log | 2.5684 | 244 | 0.6716 | 0.3922 | 0.6716 | 0.8195 |
|
| 174 |
+
| No log | 2.5895 | 246 | 0.8463 | 0.3883 | 0.8463 | 0.9199 |
|
| 175 |
+
| No log | 2.6105 | 248 | 0.9069 | 0.3402 | 0.9069 | 0.9523 |
|
| 176 |
+
| No log | 2.6316 | 250 | 0.7418 | 0.4259 | 0.7418 | 0.8613 |
|
| 177 |
+
| No log | 2.6526 | 252 | 0.6080 | 0.5125 | 0.6080 | 0.7798 |
|
| 178 |
+
| No log | 2.6737 | 254 | 0.5552 | 0.4465 | 0.5552 | 0.7451 |
|
| 179 |
+
| No log | 2.6947 | 256 | 0.5867 | 0.4622 | 0.5867 | 0.7660 |
|
| 180 |
+
| No log | 2.7158 | 258 | 0.6339 | 0.4706 | 0.6339 | 0.7962 |
|
| 181 |
+
| No log | 2.7368 | 260 | 0.6690 | 0.5044 | 0.6690 | 0.8179 |
|
| 182 |
+
| No log | 2.7579 | 262 | 0.6825 | 0.5167 | 0.6825 | 0.8261 |
|
| 183 |
+
| No log | 2.7789 | 264 | 0.6800 | 0.5143 | 0.6800 | 0.8246 |
|
| 184 |
+
| No log | 2.8 | 266 | 0.6771 | 0.5095 | 0.6771 | 0.8229 |
|
| 185 |
+
| No log | 2.8211 | 268 | 0.6573 | 0.4622 | 0.6573 | 0.8107 |
|
| 186 |
+
| No log | 2.8421 | 270 | 0.6588 | 0.4508 | 0.6588 | 0.8116 |
|
| 187 |
+
| No log | 2.8632 | 272 | 0.6727 | 0.5050 | 0.6727 | 0.8202 |
|
| 188 |
+
| No log | 2.8842 | 274 | 0.6300 | 0.5274 | 0.6300 | 0.7937 |
|
| 189 |
+
| No log | 2.9053 | 276 | 0.6290 | 0.5245 | 0.6290 | 0.7931 |
|
| 190 |
+
| No log | 2.9263 | 278 | 0.6731 | 0.5580 | 0.6731 | 0.8204 |
|
| 191 |
+
| No log | 2.9474 | 280 | 0.7603 | 0.4575 | 0.7603 | 0.8720 |
|
| 192 |
+
| No log | 2.9684 | 282 | 0.7838 | 0.4346 | 0.7838 | 0.8853 |
|
| 193 |
+
| No log | 2.9895 | 284 | 0.8229 | 0.4382 | 0.8229 | 0.9072 |
|
| 194 |
+
| No log | 3.0105 | 286 | 0.9095 | 0.4388 | 0.9095 | 0.9537 |
|
| 195 |
+
| No log | 3.0316 | 288 | 0.7786 | 0.4496 | 0.7786 | 0.8824 |
|
| 196 |
+
| No log | 3.0526 | 290 | 0.6497 | 0.5162 | 0.6497 | 0.8060 |
|
| 197 |
+
| No log | 3.0737 | 292 | 0.5631 | 0.4890 | 0.5631 | 0.7504 |
|
| 198 |
+
| No log | 3.0947 | 294 | 0.6116 | 0.4394 | 0.6116 | 0.7820 |
|
| 199 |
+
| No log | 3.1158 | 296 | 0.6838 | 0.4867 | 0.6838 | 0.8269 |
|
| 200 |
+
| No log | 3.1368 | 298 | 0.8232 | 0.4285 | 0.8232 | 0.9073 |
|
| 201 |
+
| No log | 3.1579 | 300 | 0.8734 | 0.4269 | 0.8734 | 0.9346 |
|
| 202 |
+
| No log | 3.1789 | 302 | 0.8150 | 0.4712 | 0.8150 | 0.9028 |
|
| 203 |
+
| No log | 3.2 | 304 | 0.7405 | 0.5294 | 0.7405 | 0.8605 |
|
| 204 |
+
| No log | 3.2211 | 306 | 0.6413 | 0.5176 | 0.6413 | 0.8008 |
|
| 205 |
+
| No log | 3.2421 | 308 | 0.5913 | 0.5348 | 0.5913 | 0.7689 |
|
| 206 |
+
| No log | 3.2632 | 310 | 0.5907 | 0.5172 | 0.5907 | 0.7686 |
|
| 207 |
+
| No log | 3.2842 | 312 | 0.6288 | 0.5611 | 0.6288 | 0.7930 |
|
| 208 |
+
| No log | 3.3053 | 314 | 0.6425 | 0.5611 | 0.6425 | 0.8015 |
|
| 209 |
+
| No log | 3.3263 | 316 | 0.6212 | 0.5010 | 0.6212 | 0.7882 |
|
| 210 |
+
| No log | 3.3474 | 318 | 0.5935 | 0.4746 | 0.5935 | 0.7704 |
|
| 211 |
+
| No log | 3.3684 | 320 | 0.5832 | 0.4311 | 0.5832 | 0.7637 |
|
| 212 |
+
| No log | 3.3895 | 322 | 0.5889 | 0.4639 | 0.5889 | 0.7674 |
|
| 213 |
+
| No log | 3.4105 | 324 | 0.6058 | 0.4984 | 0.6058 | 0.7783 |
|
| 214 |
+
| No log | 3.4316 | 326 | 0.6198 | 0.5541 | 0.6198 | 0.7873 |
|
| 215 |
+
| No log | 3.4526 | 328 | 0.6251 | 0.5567 | 0.6251 | 0.7906 |
|
| 216 |
+
| No log | 3.4737 | 330 | 0.6397 | 0.5262 | 0.6397 | 0.7998 |
|
| 217 |
+
| No log | 3.4947 | 332 | 0.6237 | 0.5229 | 0.6237 | 0.7897 |
|
| 218 |
+
| No log | 3.5158 | 334 | 0.6148 | 0.5372 | 0.6148 | 0.7841 |
|
| 219 |
+
| No log | 3.5368 | 336 | 0.5905 | 0.5330 | 0.5905 | 0.7685 |
|
| 220 |
+
| No log | 3.5579 | 338 | 0.5872 | 0.5450 | 0.5872 | 0.7663 |
|
| 221 |
+
| No log | 3.5789 | 340 | 0.5686 | 0.5144 | 0.5686 | 0.7541 |
|
| 222 |
+
| No log | 3.6 | 342 | 0.5612 | 0.5164 | 0.5612 | 0.7492 |
|
| 223 |
+
| No log | 3.6211 | 344 | 0.5621 | 0.5117 | 0.5621 | 0.7497 |
|
| 224 |
+
| No log | 3.6421 | 346 | 0.5519 | 0.5587 | 0.5519 | 0.7429 |
|
| 225 |
+
| No log | 3.6632 | 348 | 0.5641 | 0.5630 | 0.5641 | 0.7511 |
|
| 226 |
+
| No log | 3.6842 | 350 | 0.5928 | 0.6066 | 0.5928 | 0.7699 |
|
| 227 |
+
| No log | 3.7053 | 352 | 0.6458 | 0.5173 | 0.6458 | 0.8036 |
|
| 228 |
+
| No log | 3.7263 | 354 | 0.7049 | 0.5306 | 0.7049 | 0.8396 |
|
| 229 |
+
| No log | 3.7474 | 356 | 0.8000 | 0.4673 | 0.8000 | 0.8944 |
|
| 230 |
+
| No log | 3.7684 | 358 | 0.8399 | 0.4433 | 0.8399 | 0.9165 |
|
| 231 |
+
| No log | 3.7895 | 360 | 0.7574 | 0.4544 | 0.7574 | 0.8703 |
|
| 232 |
+
| No log | 3.8105 | 362 | 0.6814 | 0.5425 | 0.6814 | 0.8255 |
|
| 233 |
+
| No log | 3.8316 | 364 | 0.6036 | 0.5189 | 0.6036 | 0.7769 |
|
| 234 |
+
| No log | 3.8526 | 366 | 0.5701 | 0.5702 | 0.5701 | 0.7551 |
|
| 235 |
+
| No log | 3.8737 | 368 | 0.5851 | 0.5704 | 0.5851 | 0.7649 |
|
| 236 |
+
| No log | 3.8947 | 370 | 0.6450 | 0.5595 | 0.6450 | 0.8031 |
|
| 237 |
+
| No log | 3.9158 | 372 | 0.7828 | 0.4601 | 0.7828 | 0.8848 |
|
| 238 |
+
| No log | 3.9368 | 374 | 0.9965 | 0.3715 | 0.9965 | 0.9983 |
|
| 239 |
+
| No log | 3.9579 | 376 | 1.1143 | 0.2836 | 1.1143 | 1.0556 |
|
| 240 |
+
| No log | 3.9789 | 378 | 0.9718 | 0.3717 | 0.9718 | 0.9858 |
|
| 241 |
+
| No log | 4.0 | 380 | 0.7108 | 0.5453 | 0.7108 | 0.8431 |
|
| 242 |
+
| No log | 4.0211 | 382 | 0.5774 | 0.6060 | 0.5774 | 0.7599 |
|
| 243 |
+
| No log | 4.0421 | 384 | 0.5570 | 0.5410 | 0.5570 | 0.7463 |
|
| 244 |
+
| No log | 4.0632 | 386 | 0.5892 | 0.5333 | 0.5892 | 0.7676 |
|
| 245 |
+
| No log | 4.0842 | 388 | 0.6194 | 0.5241 | 0.6194 | 0.7870 |
|
| 246 |
+
| No log | 4.1053 | 390 | 0.5920 | 0.5445 | 0.5920 | 0.7694 |
|
| 247 |
+
| No log | 4.1263 | 392 | 0.5359 | 0.4936 | 0.5359 | 0.7321 |
|
| 248 |
+
| No log | 4.1474 | 394 | 0.5107 | 0.5042 | 0.5107 | 0.7146 |
|
| 249 |
+
| No log | 4.1684 | 396 | 0.5163 | 0.5408 | 0.5163 | 0.7185 |
|
| 250 |
+
| No log | 4.1895 | 398 | 0.5313 | 0.5989 | 0.5313 | 0.7289 |
|
| 251 |
+
| No log | 4.2105 | 400 | 0.5463 | 0.5777 | 0.5463 | 0.7391 |
|
| 252 |
+
| No log | 4.2316 | 402 | 0.5665 | 0.5727 | 0.5665 | 0.7527 |
|
| 253 |
+
| No log | 4.2526 | 404 | 0.6014 | 0.5768 | 0.6014 | 0.7755 |
|
| 254 |
+
| No log | 4.2737 | 406 | 0.6611 | 0.5654 | 0.6611 | 0.8131 |
|
| 255 |
+
| No log | 4.2947 | 408 | 0.7154 | 0.5310 | 0.7154 | 0.8458 |
|
| 256 |
+
| No log | 4.3158 | 410 | 0.7825 | 0.5006 | 0.7825 | 0.8846 |
|
| 257 |
+
| No log | 4.3368 | 412 | 0.8225 | 0.5012 | 0.8225 | 0.9069 |
|
| 258 |
+
| No log | 4.3579 | 414 | 0.8351 | 0.4843 | 0.8351 | 0.9139 |
|
| 259 |
+
| No log | 4.3789 | 416 | 0.8116 | 0.4926 | 0.8116 | 0.9009 |
|
| 260 |
+
| No log | 4.4 | 418 | 0.7569 | 0.4809 | 0.7569 | 0.8700 |
|
| 261 |
+
| No log | 4.4211 | 420 | 0.6994 | 0.4849 | 0.6994 | 0.8363 |
|
| 262 |
+
| No log | 4.4421 | 422 | 0.6854 | 0.4819 | 0.6854 | 0.8279 |
|
| 263 |
+
| No log | 4.4632 | 424 | 0.6971 | 0.5304 | 0.6971 | 0.8349 |
|
| 264 |
+
| No log | 4.4842 | 426 | 0.7128 | 0.5651 | 0.7128 | 0.8442 |
|
| 265 |
+
| No log | 4.5053 | 428 | 0.7769 | 0.4844 | 0.7769 | 0.8814 |
|
| 266 |
+
| No log | 4.5263 | 430 | 0.7936 | 0.4804 | 0.7936 | 0.8909 |
|
| 267 |
+
| No log | 4.5474 | 432 | 0.6638 | 0.4739 | 0.6638 | 0.8147 |
|
| 268 |
+
| No log | 4.5684 | 434 | 0.6668 | 0.5030 | 0.6668 | 0.8166 |
|
| 269 |
+
| No log | 4.5895 | 436 | 0.7087 | 0.5215 | 0.7087 | 0.8418 |
|
| 270 |
+
| No log | 4.6105 | 438 | 0.7407 | 0.5156 | 0.7407 | 0.8606 |
|
| 271 |
+
| No log | 4.6316 | 440 | 0.7848 | 0.5012 | 0.7848 | 0.8859 |
|
| 272 |
+
| No log | 4.6526 | 442 | 0.8081 | 0.5111 | 0.8081 | 0.8989 |
|
| 273 |
+
| No log | 4.6737 | 444 | 0.7567 | 0.5024 | 0.7567 | 0.8699 |
|
| 274 |
+
| No log | 4.6947 | 446 | 0.6946 | 0.5198 | 0.6946 | 0.8334 |
|
| 275 |
+
| No log | 4.7158 | 448 | 0.6577 | 0.5325 | 0.6577 | 0.8110 |
|
| 276 |
+
| No log | 4.7368 | 450 | 0.6399 | 0.5614 | 0.6399 | 0.7999 |
|
| 277 |
+
| No log | 4.7579 | 452 | 0.6201 | 0.5072 | 0.6201 | 0.7875 |
|
| 278 |
+
| No log | 4.7789 | 454 | 0.6461 | 0.5535 | 0.6461 | 0.8038 |
|
| 279 |
+
| No log | 4.8 | 456 | 0.6800 | 0.5525 | 0.6800 | 0.8246 |
|
| 280 |
+
| No log | 4.8211 | 458 | 0.7090 | 0.5176 | 0.7090 | 0.8420 |
|
| 281 |
+
| No log | 4.8421 | 460 | 0.7283 | 0.5149 | 0.7283 | 0.8534 |
|
| 282 |
+
| No log | 4.8632 | 462 | 0.7139 | 0.5349 | 0.7139 | 0.8449 |
|
| 283 |
+
| No log | 4.8842 | 464 | 0.6622 | 0.5543 | 0.6622 | 0.8138 |
|
| 284 |
+
| No log | 4.9053 | 466 | 0.6279 | 0.5405 | 0.6279 | 0.7924 |
|
| 285 |
+
| No log | 4.9263 | 468 | 0.6448 | 0.5362 | 0.6448 | 0.8030 |
|
| 286 |
+
| No log | 4.9474 | 470 | 0.6874 | 0.5685 | 0.6874 | 0.8291 |
|
| 287 |
+
| No log | 4.9684 | 472 | 0.7100 | 0.5745 | 0.7100 | 0.8426 |
|
| 288 |
+
| No log | 4.9895 | 474 | 0.7547 | 0.5324 | 0.7547 | 0.8688 |
|
| 289 |
+
| No log | 5.0105 | 476 | 0.8040 | 0.5036 | 0.8040 | 0.8967 |
|
| 290 |
+
| No log | 5.0316 | 478 | 0.8140 | 0.4906 | 0.8140 | 0.9022 |
|
| 291 |
+
| No log | 5.0526 | 480 | 0.7026 | 0.5452 | 0.7026 | 0.8382 |
|
| 292 |
+
| No log | 5.0737 | 482 | 0.5995 | 0.5783 | 0.5995 | 0.7743 |
|
| 293 |
+
| No log | 5.0947 | 484 | 0.5586 | 0.5276 | 0.5586 | 0.7474 |
|
| 294 |
+
| No log | 5.1158 | 486 | 0.5841 | 0.5174 | 0.5841 | 0.7643 |
|
| 295 |
+
| No log | 5.1368 | 488 | 0.6294 | 0.5559 | 0.6294 | 0.7933 |
|
| 296 |
+
| No log | 5.1579 | 490 | 0.6434 | 0.5541 | 0.6434 | 0.8021 |
|
| 297 |
+
| No log | 5.1789 | 492 | 0.6261 | 0.5497 | 0.6261 | 0.7913 |
|
| 298 |
+
| No log | 5.2 | 494 | 0.6209 | 0.5519 | 0.6209 | 0.7880 |
|
| 299 |
+
| No log | 5.2211 | 496 | 0.6343 | 0.5296 | 0.6343 | 0.7964 |
|
| 300 |
+
| No log | 5.2421 | 498 | 0.6715 | 0.5134 | 0.6715 | 0.8195 |
|
| 301 |
+
| 0.4009 | 5.2632 | 500 | 0.7082 | 0.5482 | 0.7082 | 0.8416 |
|
| 302 |
+
| 0.4009 | 5.2842 | 502 | 0.7507 | 0.5557 | 0.7507 | 0.8664 |
|
| 303 |
+
| 0.4009 | 5.3053 | 504 | 0.7417 | 0.5503 | 0.7417 | 0.8612 |
|
| 304 |
+
| 0.4009 | 5.3263 | 506 | 0.6898 | 0.5538 | 0.6898 | 0.8306 |
|
| 305 |
+
| 0.4009 | 5.3474 | 508 | 0.5998 | 0.5470 | 0.5998 | 0.7745 |
|
| 306 |
+
| 0.4009 | 5.3684 | 510 | 0.5250 | 0.5638 | 0.5250 | 0.7246 |
|
| 307 |
+
| 0.4009 | 5.3895 | 512 | 0.5114 | 0.5531 | 0.5114 | 0.7151 |
|
| 308 |
+
| 0.4009 | 5.4105 | 514 | 0.5244 | 0.5550 | 0.5244 | 0.7241 |
|
| 309 |
+
| 0.4009 | 5.4316 | 516 | 0.5475 | 0.5461 | 0.5475 | 0.7399 |
|
| 310 |
+
| 0.4009 | 5.4526 | 518 | 0.5598 | 0.5269 | 0.5598 | 0.7482 |
|
| 311 |
+
| 0.4009 | 5.4737 | 520 | 0.5705 | 0.4984 | 0.5705 | 0.7553 |
|
| 312 |
+
| 0.4009 | 5.4947 | 522 | 0.5705 | 0.5026 | 0.5705 | 0.7553 |
|
| 313 |
+
| 0.4009 | 5.5158 | 524 | 0.6184 | 0.5294 | 0.6184 | 0.7864 |
|
| 314 |
+
|
| 315 |
+
|
| 316 |
+
### Framework versions
|
| 317 |
+
|
| 318 |
+
- Transformers 4.44.2
|
| 319 |
+
- Pytorch 2.4.0+cu118
|
| 320 |
+
- Datasets 2.21.0
|
| 321 |
+
- 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 sha256:9a886e6a6ff773bee73bbdea677b07b77cd108011f19c7971a53fa068af2b06e
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:260cbc6e01d89cea58e1789794a76164a491af63895c0f24b98c0bfba73f6bea
|
| 3 |
+
size 5240
|