Training in progress, step 500
Browse files- README.md +333 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k15_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_OSS_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k15_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: 0.5646
|
| 19 |
+
- Qwk: 0.5418
|
| 20 |
+
- Mse: 0.5646
|
| 21 |
+
- Rmse: 0.7514
|
| 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 | 0.0267 | 2 | 2.4925 | 0.0222 | 2.4925 | 1.5788 |
|
| 53 |
+
| No log | 0.0533 | 4 | 1.1230 | 0.2335 | 1.1230 | 1.0597 |
|
| 54 |
+
| No log | 0.08 | 6 | 0.8509 | 0.1372 | 0.8509 | 0.9225 |
|
| 55 |
+
| No log | 0.1067 | 8 | 0.8248 | 0.1815 | 0.8248 | 0.9082 |
|
| 56 |
+
| No log | 0.1333 | 10 | 1.0058 | 0.2282 | 1.0058 | 1.0029 |
|
| 57 |
+
| No log | 0.16 | 12 | 1.0425 | 0.2499 | 1.0425 | 1.0210 |
|
| 58 |
+
| No log | 0.1867 | 14 | 0.8766 | 0.3006 | 0.8766 | 0.9363 |
|
| 59 |
+
| No log | 0.2133 | 16 | 0.6619 | 0.2243 | 0.6619 | 0.8136 |
|
| 60 |
+
| No log | 0.24 | 18 | 0.6750 | 0.2019 | 0.6750 | 0.8216 |
|
| 61 |
+
| No log | 0.2667 | 20 | 0.7474 | 0.3060 | 0.7474 | 0.8645 |
|
| 62 |
+
| No log | 0.2933 | 22 | 0.7129 | 0.2051 | 0.7129 | 0.8443 |
|
| 63 |
+
| No log | 0.32 | 24 | 0.7372 | 0.0784 | 0.7372 | 0.8586 |
|
| 64 |
+
| No log | 0.3467 | 26 | 0.6809 | 0.3258 | 0.6809 | 0.8252 |
|
| 65 |
+
| No log | 0.3733 | 28 | 0.5893 | 0.4171 | 0.5893 | 0.7676 |
|
| 66 |
+
| No log | 0.4 | 30 | 0.5740 | 0.4493 | 0.5740 | 0.7577 |
|
| 67 |
+
| No log | 0.4267 | 32 | 0.6392 | 0.5081 | 0.6392 | 0.7995 |
|
| 68 |
+
| No log | 0.4533 | 34 | 0.5834 | 0.4661 | 0.5834 | 0.7638 |
|
| 69 |
+
| No log | 0.48 | 36 | 0.6116 | 0.4795 | 0.6116 | 0.7821 |
|
| 70 |
+
| No log | 0.5067 | 38 | 0.8681 | 0.4462 | 0.8681 | 0.9317 |
|
| 71 |
+
| No log | 0.5333 | 40 | 0.8940 | 0.3909 | 0.8940 | 0.9455 |
|
| 72 |
+
| No log | 0.56 | 42 | 0.7679 | 0.3981 | 0.7679 | 0.8763 |
|
| 73 |
+
| No log | 0.5867 | 44 | 0.5948 | 0.5308 | 0.5948 | 0.7712 |
|
| 74 |
+
| No log | 0.6133 | 46 | 0.5472 | 0.4536 | 0.5472 | 0.7398 |
|
| 75 |
+
| No log | 0.64 | 48 | 0.5576 | 0.4139 | 0.5576 | 0.7467 |
|
| 76 |
+
| No log | 0.6667 | 50 | 0.5568 | 0.5075 | 0.5568 | 0.7462 |
|
| 77 |
+
| No log | 0.6933 | 52 | 0.5391 | 0.5518 | 0.5391 | 0.7342 |
|
| 78 |
+
| No log | 0.72 | 54 | 0.5760 | 0.4808 | 0.5760 | 0.7589 |
|
| 79 |
+
| No log | 0.7467 | 56 | 0.5523 | 0.5397 | 0.5523 | 0.7431 |
|
| 80 |
+
| No log | 0.7733 | 58 | 0.6236 | 0.6118 | 0.6236 | 0.7897 |
|
| 81 |
+
| No log | 0.8 | 60 | 0.6306 | 0.5652 | 0.6306 | 0.7941 |
|
| 82 |
+
| No log | 0.8267 | 62 | 0.6921 | 0.5062 | 0.6921 | 0.8319 |
|
| 83 |
+
| No log | 0.8533 | 64 | 0.7350 | 0.4853 | 0.7350 | 0.8573 |
|
| 84 |
+
| No log | 0.88 | 66 | 0.6936 | 0.5321 | 0.6936 | 0.8328 |
|
| 85 |
+
| No log | 0.9067 | 68 | 0.6267 | 0.5257 | 0.6267 | 0.7917 |
|
| 86 |
+
| No log | 0.9333 | 70 | 0.5934 | 0.5288 | 0.5934 | 0.7704 |
|
| 87 |
+
| No log | 0.96 | 72 | 0.6346 | 0.4955 | 0.6346 | 0.7966 |
|
| 88 |
+
| No log | 0.9867 | 74 | 0.6162 | 0.4800 | 0.6162 | 0.7850 |
|
| 89 |
+
| No log | 1.0133 | 76 | 0.5919 | 0.56 | 0.5919 | 0.7694 |
|
| 90 |
+
| No log | 1.04 | 78 | 0.7384 | 0.4247 | 0.7384 | 0.8593 |
|
| 91 |
+
| No log | 1.0667 | 80 | 1.0479 | 0.3442 | 1.0479 | 1.0237 |
|
| 92 |
+
| No log | 1.0933 | 82 | 0.9285 | 0.4948 | 0.9285 | 0.9636 |
|
| 93 |
+
| No log | 1.12 | 84 | 0.6293 | 0.5293 | 0.6293 | 0.7933 |
|
| 94 |
+
| No log | 1.1467 | 86 | 0.6712 | 0.5209 | 0.6712 | 0.8192 |
|
| 95 |
+
| No log | 1.1733 | 88 | 0.7398 | 0.5152 | 0.7398 | 0.8601 |
|
| 96 |
+
| No log | 1.2 | 90 | 0.6804 | 0.5108 | 0.6804 | 0.8249 |
|
| 97 |
+
| No log | 1.2267 | 92 | 0.6458 | 0.4806 | 0.6458 | 0.8036 |
|
| 98 |
+
| No log | 1.2533 | 94 | 0.7654 | 0.4250 | 0.7654 | 0.8749 |
|
| 99 |
+
| No log | 1.28 | 96 | 0.8641 | 0.4118 | 0.8641 | 0.9296 |
|
| 100 |
+
| No log | 1.3067 | 98 | 0.8400 | 0.4277 | 0.8400 | 0.9165 |
|
| 101 |
+
| No log | 1.3333 | 100 | 0.8637 | 0.4573 | 0.8637 | 0.9294 |
|
| 102 |
+
| No log | 1.3600 | 102 | 0.7998 | 0.4539 | 0.7998 | 0.8943 |
|
| 103 |
+
| No log | 1.3867 | 104 | 0.8032 | 0.4493 | 0.8032 | 0.8962 |
|
| 104 |
+
| No log | 1.4133 | 106 | 0.7761 | 0.4493 | 0.7761 | 0.8810 |
|
| 105 |
+
| No log | 1.44 | 108 | 0.7144 | 0.4819 | 0.7144 | 0.8452 |
|
| 106 |
+
| No log | 1.4667 | 110 | 0.7175 | 0.5038 | 0.7175 | 0.8470 |
|
| 107 |
+
| No log | 1.4933 | 112 | 0.6975 | 0.4847 | 0.6975 | 0.8351 |
|
| 108 |
+
| No log | 1.52 | 114 | 0.7861 | 0.4619 | 0.7861 | 0.8866 |
|
| 109 |
+
| No log | 1.5467 | 116 | 0.7757 | 0.5431 | 0.7757 | 0.8808 |
|
| 110 |
+
| No log | 1.5733 | 118 | 0.7487 | 0.4997 | 0.7487 | 0.8653 |
|
| 111 |
+
| No log | 1.6 | 120 | 0.8485 | 0.5309 | 0.8485 | 0.9211 |
|
| 112 |
+
| No log | 1.6267 | 122 | 0.7618 | 0.4735 | 0.7618 | 0.8728 |
|
| 113 |
+
| No log | 1.6533 | 124 | 0.6697 | 0.4386 | 0.6697 | 0.8183 |
|
| 114 |
+
| No log | 1.6800 | 126 | 0.6568 | 0.5508 | 0.6568 | 0.8104 |
|
| 115 |
+
| No log | 1.7067 | 128 | 0.6956 | 0.4930 | 0.6956 | 0.8340 |
|
| 116 |
+
| No log | 1.7333 | 130 | 0.6408 | 0.5508 | 0.6408 | 0.8005 |
|
| 117 |
+
| No log | 1.76 | 132 | 0.5603 | 0.4941 | 0.5603 | 0.7485 |
|
| 118 |
+
| No log | 1.7867 | 134 | 0.5972 | 0.5479 | 0.5972 | 0.7728 |
|
| 119 |
+
| No log | 1.8133 | 136 | 0.5663 | 0.5190 | 0.5663 | 0.7525 |
|
| 120 |
+
| No log | 1.8400 | 138 | 0.5723 | 0.5639 | 0.5723 | 0.7565 |
|
| 121 |
+
| No log | 1.8667 | 140 | 0.7406 | 0.5517 | 0.7406 | 0.8606 |
|
| 122 |
+
| No log | 1.8933 | 142 | 0.7525 | 0.4592 | 0.7525 | 0.8675 |
|
| 123 |
+
| No log | 1.92 | 144 | 0.6493 | 0.5567 | 0.6493 | 0.8058 |
|
| 124 |
+
| No log | 1.9467 | 146 | 0.6634 | 0.6076 | 0.6634 | 0.8145 |
|
| 125 |
+
| No log | 1.9733 | 148 | 0.6974 | 0.5260 | 0.6974 | 0.8351 |
|
| 126 |
+
| No log | 2.0 | 150 | 0.6333 | 0.4759 | 0.6333 | 0.7958 |
|
| 127 |
+
| No log | 2.0267 | 152 | 0.6676 | 0.5787 | 0.6676 | 0.8171 |
|
| 128 |
+
| No log | 2.0533 | 154 | 0.7065 | 0.5402 | 0.7065 | 0.8406 |
|
| 129 |
+
| No log | 2.08 | 156 | 0.6062 | 0.5201 | 0.6062 | 0.7786 |
|
| 130 |
+
| No log | 2.1067 | 158 | 0.5455 | 0.6052 | 0.5455 | 0.7386 |
|
| 131 |
+
| No log | 2.1333 | 160 | 0.5549 | 0.5071 | 0.5549 | 0.7449 |
|
| 132 |
+
| No log | 2.16 | 162 | 0.5899 | 0.5457 | 0.5899 | 0.7681 |
|
| 133 |
+
| No log | 2.1867 | 164 | 0.6885 | 0.5789 | 0.6885 | 0.8297 |
|
| 134 |
+
| No log | 2.2133 | 166 | 0.7642 | 0.4925 | 0.7642 | 0.8742 |
|
| 135 |
+
| No log | 2.24 | 168 | 0.6945 | 0.5529 | 0.6945 | 0.8334 |
|
| 136 |
+
| No log | 2.2667 | 170 | 0.6242 | 0.5552 | 0.6242 | 0.7901 |
|
| 137 |
+
| No log | 2.2933 | 172 | 0.6144 | 0.5225 | 0.6144 | 0.7839 |
|
| 138 |
+
| No log | 2.32 | 174 | 0.6039 | 0.4550 | 0.6039 | 0.7771 |
|
| 139 |
+
| No log | 2.3467 | 176 | 0.6079 | 0.5148 | 0.6079 | 0.7797 |
|
| 140 |
+
| No log | 2.3733 | 178 | 0.7349 | 0.5118 | 0.7349 | 0.8573 |
|
| 141 |
+
| No log | 2.4 | 180 | 0.7917 | 0.4794 | 0.7917 | 0.8898 |
|
| 142 |
+
| No log | 2.4267 | 182 | 0.7804 | 0.4858 | 0.7804 | 0.8834 |
|
| 143 |
+
| No log | 2.4533 | 184 | 0.6626 | 0.5008 | 0.6626 | 0.8140 |
|
| 144 |
+
| No log | 2.48 | 186 | 0.6164 | 0.5811 | 0.6164 | 0.7851 |
|
| 145 |
+
| No log | 2.5067 | 188 | 0.6617 | 0.5698 | 0.6617 | 0.8134 |
|
| 146 |
+
| No log | 2.5333 | 190 | 0.6411 | 0.6055 | 0.6411 | 0.8007 |
|
| 147 |
+
| No log | 2.56 | 192 | 0.6556 | 0.6137 | 0.6556 | 0.8097 |
|
| 148 |
+
| No log | 2.5867 | 194 | 0.6709 | 0.5520 | 0.6709 | 0.8191 |
|
| 149 |
+
| No log | 2.6133 | 196 | 0.6059 | 0.4568 | 0.6059 | 0.7784 |
|
| 150 |
+
| No log | 2.64 | 198 | 0.5892 | 0.5113 | 0.5892 | 0.7676 |
|
| 151 |
+
| No log | 2.6667 | 200 | 0.6683 | 0.5103 | 0.6683 | 0.8175 |
|
| 152 |
+
| No log | 2.6933 | 202 | 0.6350 | 0.5692 | 0.6350 | 0.7969 |
|
| 153 |
+
| No log | 2.7200 | 204 | 0.6188 | 0.5471 | 0.6188 | 0.7866 |
|
| 154 |
+
| No log | 2.7467 | 206 | 0.5842 | 0.5692 | 0.5842 | 0.7643 |
|
| 155 |
+
| No log | 2.7733 | 208 | 0.5206 | 0.5738 | 0.5206 | 0.7215 |
|
| 156 |
+
| No log | 2.8 | 210 | 0.5107 | 0.5902 | 0.5107 | 0.7146 |
|
| 157 |
+
| No log | 2.8267 | 212 | 0.5159 | 0.6359 | 0.5159 | 0.7183 |
|
| 158 |
+
| No log | 2.8533 | 214 | 0.5502 | 0.5219 | 0.5502 | 0.7418 |
|
| 159 |
+
| No log | 2.88 | 216 | 0.6123 | 0.5026 | 0.6123 | 0.7825 |
|
| 160 |
+
| No log | 2.9067 | 218 | 0.5814 | 0.5342 | 0.5814 | 0.7625 |
|
| 161 |
+
| No log | 2.9333 | 220 | 0.5932 | 0.5998 | 0.5932 | 0.7702 |
|
| 162 |
+
| No log | 2.96 | 222 | 0.5980 | 0.6107 | 0.5980 | 0.7733 |
|
| 163 |
+
| No log | 2.9867 | 224 | 0.5978 | 0.5847 | 0.5978 | 0.7732 |
|
| 164 |
+
| No log | 3.0133 | 226 | 0.6024 | 0.5900 | 0.6024 | 0.7761 |
|
| 165 |
+
| No log | 3.04 | 228 | 0.6819 | 0.5323 | 0.6819 | 0.8258 |
|
| 166 |
+
| No log | 3.0667 | 230 | 0.8041 | 0.4965 | 0.8041 | 0.8967 |
|
| 167 |
+
| No log | 3.0933 | 232 | 0.7635 | 0.4717 | 0.7635 | 0.8738 |
|
| 168 |
+
| No log | 3.12 | 234 | 0.6171 | 0.5085 | 0.6171 | 0.7856 |
|
| 169 |
+
| No log | 3.1467 | 236 | 0.5317 | 0.5771 | 0.5317 | 0.7292 |
|
| 170 |
+
| No log | 3.1733 | 238 | 0.6117 | 0.4673 | 0.6117 | 0.7821 |
|
| 171 |
+
| No log | 3.2 | 240 | 0.6778 | 0.5077 | 0.6778 | 0.8233 |
|
| 172 |
+
| No log | 3.2267 | 242 | 0.6256 | 0.5368 | 0.6256 | 0.7909 |
|
| 173 |
+
| No log | 3.2533 | 244 | 0.5850 | 0.6322 | 0.5850 | 0.7648 |
|
| 174 |
+
| No log | 3.2800 | 246 | 0.5458 | 0.6210 | 0.5458 | 0.7387 |
|
| 175 |
+
| No log | 3.3067 | 248 | 0.5224 | 0.5872 | 0.5224 | 0.7228 |
|
| 176 |
+
| No log | 3.3333 | 250 | 0.5279 | 0.5859 | 0.5279 | 0.7266 |
|
| 177 |
+
| No log | 3.36 | 252 | 0.5397 | 0.5859 | 0.5397 | 0.7347 |
|
| 178 |
+
| No log | 3.3867 | 254 | 0.5575 | 0.6075 | 0.5575 | 0.7467 |
|
| 179 |
+
| No log | 3.4133 | 256 | 0.6157 | 0.6279 | 0.6157 | 0.7847 |
|
| 180 |
+
| No log | 3.44 | 258 | 0.7158 | 0.6028 | 0.7158 | 0.8461 |
|
| 181 |
+
| No log | 3.4667 | 260 | 0.7189 | 0.5704 | 0.7189 | 0.8479 |
|
| 182 |
+
| No log | 3.4933 | 262 | 0.7359 | 0.5827 | 0.7359 | 0.8578 |
|
| 183 |
+
| No log | 3.52 | 264 | 0.6809 | 0.5278 | 0.6809 | 0.8252 |
|
| 184 |
+
| No log | 3.5467 | 266 | 0.7296 | 0.5632 | 0.7296 | 0.8542 |
|
| 185 |
+
| No log | 3.5733 | 268 | 0.8372 | 0.4821 | 0.8372 | 0.9150 |
|
| 186 |
+
| No log | 3.6 | 270 | 0.8485 | 0.4106 | 0.8485 | 0.9211 |
|
| 187 |
+
| No log | 3.6267 | 272 | 0.7450 | 0.4419 | 0.7450 | 0.8631 |
|
| 188 |
+
| No log | 3.6533 | 274 | 0.6330 | 0.4836 | 0.6330 | 0.7956 |
|
| 189 |
+
| No log | 3.68 | 276 | 0.6142 | 0.5059 | 0.6142 | 0.7837 |
|
| 190 |
+
| No log | 3.7067 | 278 | 0.6478 | 0.5059 | 0.6478 | 0.8049 |
|
| 191 |
+
| No log | 3.7333 | 280 | 0.7433 | 0.5520 | 0.7433 | 0.8621 |
|
| 192 |
+
| No log | 3.76 | 282 | 0.8736 | 0.4831 | 0.8736 | 0.9347 |
|
| 193 |
+
| No log | 3.7867 | 284 | 0.8497 | 0.4831 | 0.8497 | 0.9218 |
|
| 194 |
+
| No log | 3.8133 | 286 | 0.7172 | 0.5533 | 0.7172 | 0.8469 |
|
| 195 |
+
| No log | 3.84 | 288 | 0.6028 | 0.5211 | 0.6028 | 0.7764 |
|
| 196 |
+
| No log | 3.8667 | 290 | 0.5637 | 0.5786 | 0.5637 | 0.7508 |
|
| 197 |
+
| No log | 3.8933 | 292 | 0.5382 | 0.5813 | 0.5382 | 0.7336 |
|
| 198 |
+
| No log | 3.92 | 294 | 0.5312 | 0.5222 | 0.5312 | 0.7288 |
|
| 199 |
+
| No log | 3.9467 | 296 | 0.5499 | 0.5308 | 0.5499 | 0.7415 |
|
| 200 |
+
| No log | 3.9733 | 298 | 0.5682 | 0.5845 | 0.5682 | 0.7538 |
|
| 201 |
+
| No log | 4.0 | 300 | 0.5857 | 0.5827 | 0.5857 | 0.7653 |
|
| 202 |
+
| No log | 4.0267 | 302 | 0.6489 | 0.6188 | 0.6489 | 0.8055 |
|
| 203 |
+
| No log | 4.0533 | 304 | 0.7402 | 0.5385 | 0.7402 | 0.8603 |
|
| 204 |
+
| No log | 4.08 | 306 | 0.7590 | 0.5281 | 0.7590 | 0.8712 |
|
| 205 |
+
| No log | 4.1067 | 308 | 0.6734 | 0.5692 | 0.6734 | 0.8206 |
|
| 206 |
+
| No log | 4.1333 | 310 | 0.6166 | 0.5653 | 0.6166 | 0.7852 |
|
| 207 |
+
| No log | 4.16 | 312 | 0.6122 | 0.5653 | 0.6122 | 0.7824 |
|
| 208 |
+
| No log | 4.1867 | 314 | 0.6277 | 0.4759 | 0.6277 | 0.7923 |
|
| 209 |
+
| No log | 4.2133 | 316 | 0.6333 | 0.4759 | 0.6333 | 0.7958 |
|
| 210 |
+
| No log | 4.24 | 318 | 0.6535 | 0.4920 | 0.6535 | 0.8084 |
|
| 211 |
+
| No log | 4.2667 | 320 | 0.6437 | 0.6092 | 0.6437 | 0.8023 |
|
| 212 |
+
| No log | 4.2933 | 322 | 0.6715 | 0.5626 | 0.6715 | 0.8194 |
|
| 213 |
+
| No log | 4.32 | 324 | 0.6450 | 0.5038 | 0.6450 | 0.8031 |
|
| 214 |
+
| No log | 4.3467 | 326 | 0.6423 | 0.4531 | 0.6423 | 0.8015 |
|
| 215 |
+
| No log | 4.3733 | 328 | 0.6797 | 0.4008 | 0.6797 | 0.8244 |
|
| 216 |
+
| No log | 4.4 | 330 | 0.6558 | 0.4230 | 0.6558 | 0.8098 |
|
| 217 |
+
| No log | 4.4267 | 332 | 0.6726 | 0.3777 | 0.6726 | 0.8201 |
|
| 218 |
+
| No log | 4.4533 | 334 | 0.6360 | 0.4051 | 0.6360 | 0.7975 |
|
| 219 |
+
| No log | 4.48 | 336 | 0.6419 | 0.5396 | 0.6419 | 0.8012 |
|
| 220 |
+
| No log | 4.5067 | 338 | 0.6353 | 0.5942 | 0.6353 | 0.7971 |
|
| 221 |
+
| No log | 4.5333 | 340 | 0.6108 | 0.5954 | 0.6108 | 0.7816 |
|
| 222 |
+
| No log | 4.5600 | 342 | 0.5793 | 0.5886 | 0.5793 | 0.7611 |
|
| 223 |
+
| No log | 4.5867 | 344 | 0.5490 | 0.5845 | 0.5490 | 0.7410 |
|
| 224 |
+
| No log | 4.6133 | 346 | 0.5439 | 0.5632 | 0.5439 | 0.7375 |
|
| 225 |
+
| No log | 4.64 | 348 | 0.5602 | 0.5254 | 0.5602 | 0.7484 |
|
| 226 |
+
| No log | 4.6667 | 350 | 0.6194 | 0.4562 | 0.6194 | 0.7870 |
|
| 227 |
+
| No log | 4.6933 | 352 | 0.6326 | 0.4646 | 0.6326 | 0.7954 |
|
| 228 |
+
| No log | 4.72 | 354 | 0.6060 | 0.4602 | 0.6060 | 0.7785 |
|
| 229 |
+
| No log | 4.7467 | 356 | 0.6540 | 0.4726 | 0.6540 | 0.8087 |
|
| 230 |
+
| No log | 4.7733 | 358 | 0.7311 | 0.4705 | 0.7311 | 0.8551 |
|
| 231 |
+
| No log | 4.8 | 360 | 0.6694 | 0.5263 | 0.6694 | 0.8182 |
|
| 232 |
+
| No log | 4.8267 | 362 | 0.5807 | 0.5897 | 0.5807 | 0.7620 |
|
| 233 |
+
| No log | 4.8533 | 364 | 0.5969 | 0.5142 | 0.5969 | 0.7726 |
|
| 234 |
+
| No log | 4.88 | 366 | 0.6539 | 0.5030 | 0.6539 | 0.8086 |
|
| 235 |
+
| No log | 4.9067 | 368 | 0.6524 | 0.5502 | 0.6524 | 0.8077 |
|
| 236 |
+
| No log | 4.9333 | 370 | 0.6570 | 0.6145 | 0.6570 | 0.8106 |
|
| 237 |
+
| No log | 4.96 | 372 | 0.6958 | 0.6035 | 0.6958 | 0.8341 |
|
| 238 |
+
| No log | 4.9867 | 374 | 0.6388 | 0.6034 | 0.6388 | 0.7993 |
|
| 239 |
+
| No log | 5.0133 | 376 | 0.5513 | 0.5970 | 0.5513 | 0.7425 |
|
| 240 |
+
| No log | 5.04 | 378 | 0.5149 | 0.5899 | 0.5149 | 0.7176 |
|
| 241 |
+
| No log | 5.0667 | 380 | 0.4973 | 0.5738 | 0.4973 | 0.7052 |
|
| 242 |
+
| No log | 5.0933 | 382 | 0.4869 | 0.5272 | 0.4869 | 0.6978 |
|
| 243 |
+
| No log | 5.12 | 384 | 0.5129 | 0.5468 | 0.5129 | 0.7161 |
|
| 244 |
+
| No log | 5.1467 | 386 | 0.5681 | 0.5653 | 0.5681 | 0.7537 |
|
| 245 |
+
| No log | 5.1733 | 388 | 0.6333 | 0.5939 | 0.6333 | 0.7958 |
|
| 246 |
+
| No log | 5.2 | 390 | 0.6457 | 0.5748 | 0.6457 | 0.8036 |
|
| 247 |
+
| No log | 5.2267 | 392 | 0.6606 | 0.5595 | 0.6606 | 0.8128 |
|
| 248 |
+
| No log | 5.2533 | 394 | 0.6496 | 0.5814 | 0.6496 | 0.8060 |
|
| 249 |
+
| No log | 5.28 | 396 | 0.6218 | 0.5335 | 0.6218 | 0.7886 |
|
| 250 |
+
| No log | 5.3067 | 398 | 0.6216 | 0.5930 | 0.6216 | 0.7884 |
|
| 251 |
+
| No log | 5.3333 | 400 | 0.6057 | 0.5884 | 0.6057 | 0.7783 |
|
| 252 |
+
| No log | 5.36 | 402 | 0.5850 | 0.5884 | 0.5850 | 0.7648 |
|
| 253 |
+
| No log | 5.3867 | 404 | 0.5812 | 0.6238 | 0.5812 | 0.7623 |
|
| 254 |
+
| No log | 5.4133 | 406 | 0.5455 | 0.5947 | 0.5455 | 0.7386 |
|
| 255 |
+
| No log | 5.44 | 408 | 0.5374 | 0.5568 | 0.5374 | 0.7331 |
|
| 256 |
+
| No log | 5.4667 | 410 | 0.5588 | 0.5275 | 0.5588 | 0.7475 |
|
| 257 |
+
| No log | 5.4933 | 412 | 0.5880 | 0.5275 | 0.5880 | 0.7668 |
|
| 258 |
+
| No log | 5.52 | 414 | 0.6308 | 0.5658 | 0.6308 | 0.7942 |
|
| 259 |
+
| No log | 5.5467 | 416 | 0.6186 | 0.5918 | 0.6186 | 0.7865 |
|
| 260 |
+
| No log | 5.5733 | 418 | 0.6540 | 0.5722 | 0.6540 | 0.8087 |
|
| 261 |
+
| No log | 5.6 | 420 | 0.6251 | 0.5431 | 0.6251 | 0.7906 |
|
| 262 |
+
| No log | 5.6267 | 422 | 0.5750 | 0.5512 | 0.5750 | 0.7583 |
|
| 263 |
+
| No log | 5.6533 | 424 | 0.5568 | 0.5291 | 0.5568 | 0.7462 |
|
| 264 |
+
| No log | 5.68 | 426 | 0.5842 | 0.5326 | 0.5842 | 0.7643 |
|
| 265 |
+
| No log | 5.7067 | 428 | 0.6361 | 0.4862 | 0.6361 | 0.7976 |
|
| 266 |
+
| No log | 5.7333 | 430 | 0.6407 | 0.5227 | 0.6407 | 0.8004 |
|
| 267 |
+
| No log | 5.76 | 432 | 0.5826 | 0.5410 | 0.5826 | 0.7633 |
|
| 268 |
+
| No log | 5.7867 | 434 | 0.6003 | 0.5814 | 0.6003 | 0.7748 |
|
| 269 |
+
| No log | 5.8133 | 436 | 0.5958 | 0.5811 | 0.5958 | 0.7719 |
|
| 270 |
+
| No log | 5.84 | 438 | 0.6167 | 0.6221 | 0.6167 | 0.7853 |
|
| 271 |
+
| No log | 5.8667 | 440 | 0.5881 | 0.6279 | 0.5881 | 0.7669 |
|
| 272 |
+
| No log | 5.8933 | 442 | 0.5454 | 0.5786 | 0.5454 | 0.7385 |
|
| 273 |
+
| No log | 5.92 | 444 | 0.5283 | 0.5687 | 0.5283 | 0.7268 |
|
| 274 |
+
| No log | 5.9467 | 446 | 0.5898 | 0.5774 | 0.5898 | 0.7680 |
|
| 275 |
+
| No log | 5.9733 | 448 | 0.6241 | 0.5893 | 0.6241 | 0.7900 |
|
| 276 |
+
| No log | 6.0 | 450 | 0.6203 | 0.6073 | 0.6203 | 0.7876 |
|
| 277 |
+
| No log | 6.0267 | 452 | 0.6430 | 0.6377 | 0.6430 | 0.8019 |
|
| 278 |
+
| No log | 6.0533 | 454 | 0.6484 | 0.6167 | 0.6484 | 0.8052 |
|
| 279 |
+
| No log | 6.08 | 456 | 0.6636 | 0.5453 | 0.6636 | 0.8146 |
|
| 280 |
+
| No log | 6.1067 | 458 | 0.7031 | 0.6058 | 0.7031 | 0.8385 |
|
| 281 |
+
| No log | 6.1333 | 460 | 0.6541 | 0.5723 | 0.6541 | 0.8087 |
|
| 282 |
+
| No log | 6.16 | 462 | 0.6062 | 0.5622 | 0.6062 | 0.7786 |
|
| 283 |
+
| No log | 6.1867 | 464 | 0.6321 | 0.6361 | 0.6321 | 0.7951 |
|
| 284 |
+
| No log | 6.2133 | 466 | 0.6461 | 0.5789 | 0.6461 | 0.8038 |
|
| 285 |
+
| No log | 6.24 | 468 | 0.6045 | 0.5624 | 0.6045 | 0.7775 |
|
| 286 |
+
| No log | 6.2667 | 470 | 0.5451 | 0.5426 | 0.5451 | 0.7383 |
|
| 287 |
+
| No log | 6.2933 | 472 | 0.5309 | 0.5034 | 0.5309 | 0.7286 |
|
| 288 |
+
| No log | 6.32 | 474 | 0.5405 | 0.4979 | 0.5405 | 0.7352 |
|
| 289 |
+
| No log | 6.3467 | 476 | 0.5731 | 0.5045 | 0.5731 | 0.7570 |
|
| 290 |
+
| No log | 6.3733 | 478 | 0.5828 | 0.5744 | 0.5828 | 0.7634 |
|
| 291 |
+
| No log | 6.4 | 480 | 0.6116 | 0.5403 | 0.6116 | 0.7820 |
|
| 292 |
+
| No log | 6.4267 | 482 | 0.6252 | 0.5445 | 0.6252 | 0.7907 |
|
| 293 |
+
| No log | 6.4533 | 484 | 0.5998 | 0.5679 | 0.5998 | 0.7745 |
|
| 294 |
+
| No log | 6.48 | 486 | 0.5767 | 0.4986 | 0.5767 | 0.7594 |
|
| 295 |
+
| No log | 6.5067 | 488 | 0.5543 | 0.4986 | 0.5543 | 0.7445 |
|
| 296 |
+
| No log | 6.5333 | 490 | 0.5390 | 0.4514 | 0.5390 | 0.7342 |
|
| 297 |
+
| No log | 6.5600 | 492 | 0.5401 | 0.4724 | 0.5401 | 0.7349 |
|
| 298 |
+
| No log | 6.5867 | 494 | 0.5746 | 0.5512 | 0.5746 | 0.7580 |
|
| 299 |
+
| No log | 6.6133 | 496 | 0.6906 | 0.5548 | 0.6906 | 0.8310 |
|
| 300 |
+
| No log | 6.64 | 498 | 0.7605 | 0.4704 | 0.7605 | 0.8721 |
|
| 301 |
+
| 0.304 | 6.6667 | 500 | 0.7141 | 0.5747 | 0.7141 | 0.8451 |
|
| 302 |
+
| 0.304 | 6.6933 | 502 | 0.6164 | 0.5858 | 0.6164 | 0.7851 |
|
| 303 |
+
| 0.304 | 6.72 | 504 | 0.5609 | 0.5353 | 0.5609 | 0.7489 |
|
| 304 |
+
| 0.304 | 6.7467 | 506 | 0.5954 | 0.5098 | 0.5954 | 0.7716 |
|
| 305 |
+
| 0.304 | 6.7733 | 508 | 0.5939 | 0.5041 | 0.5939 | 0.7706 |
|
| 306 |
+
| 0.304 | 6.8 | 510 | 0.5558 | 0.5254 | 0.5558 | 0.7455 |
|
| 307 |
+
| 0.304 | 6.8267 | 512 | 0.5559 | 0.6330 | 0.5559 | 0.7456 |
|
| 308 |
+
| 0.304 | 6.8533 | 514 | 0.6770 | 0.5508 | 0.6770 | 0.8228 |
|
| 309 |
+
| 0.304 | 6.88 | 516 | 0.7195 | 0.5118 | 0.7195 | 0.8482 |
|
| 310 |
+
| 0.304 | 6.9067 | 518 | 0.6352 | 0.5310 | 0.6352 | 0.7970 |
|
| 311 |
+
| 0.304 | 6.9333 | 520 | 0.5311 | 0.5906 | 0.5311 | 0.7288 |
|
| 312 |
+
| 0.304 | 6.96 | 522 | 0.4882 | 0.5711 | 0.4882 | 0.6987 |
|
| 313 |
+
| 0.304 | 6.9867 | 524 | 0.5247 | 0.5421 | 0.5247 | 0.7244 |
|
| 314 |
+
| 0.304 | 7.0133 | 526 | 0.5199 | 0.5692 | 0.5199 | 0.7210 |
|
| 315 |
+
| 0.304 | 7.04 | 528 | 0.4988 | 0.5813 | 0.4988 | 0.7063 |
|
| 316 |
+
| 0.304 | 7.0667 | 530 | 0.5388 | 0.6109 | 0.5388 | 0.7341 |
|
| 317 |
+
| 0.304 | 7.0933 | 532 | 0.6592 | 0.5167 | 0.6592 | 0.8119 |
|
| 318 |
+
| 0.304 | 7.12 | 534 | 0.7583 | 0.5190 | 0.7583 | 0.8708 |
|
| 319 |
+
| 0.304 | 7.1467 | 536 | 0.7162 | 0.5190 | 0.7162 | 0.8463 |
|
| 320 |
+
| 0.304 | 7.1733 | 538 | 0.5941 | 0.6113 | 0.5941 | 0.7708 |
|
| 321 |
+
| 0.304 | 7.2 | 540 | 0.4976 | 0.4661 | 0.4976 | 0.7054 |
|
| 322 |
+
| 0.304 | 7.2267 | 542 | 0.4856 | 0.5472 | 0.4856 | 0.6969 |
|
| 323 |
+
| 0.304 | 7.2533 | 544 | 0.4869 | 0.5306 | 0.4869 | 0.6978 |
|
| 324 |
+
| 0.304 | 7.28 | 546 | 0.4970 | 0.5053 | 0.4970 | 0.7050 |
|
| 325 |
+
| 0.304 | 7.3067 | 548 | 0.5646 | 0.5418 | 0.5646 | 0.7514 |
|
| 326 |
+
|
| 327 |
+
|
| 328 |
+
### Framework versions
|
| 329 |
+
|
| 330 |
+
- Transformers 4.44.2
|
| 331 |
+
- Pytorch 2.4.0+cu118
|
| 332 |
+
- Datasets 2.21.0
|
| 333 |
+
- 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 sha256:199ce3fe7b8f78660b2894631cc29544efc5d5b1800f985c3698b8c079cffbe7
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28cd6289c64905b895651c800870cd3618286225ccb6d0bef0783ab44cc98ca8
|
| 3 |
+
size 5304
|