Training in progress, step 500
Browse files- README.md +317 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_run2_AugV5_k18_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_run2_AugV5_k18_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: 0.4551
|
| 19 |
+
- Qwk: 0.5324
|
| 20 |
+
- Mse: 0.4551
|
| 21 |
+
- Rmse: 0.6746
|
| 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 | 0.0222 | 2 | 2.4467 | -0.0136 | 2.4467 | 1.5642 |
|
| 53 |
+
| No log | 0.0444 | 4 | 1.4423 | 0.1230 | 1.4423 | 1.2010 |
|
| 54 |
+
| No log | 0.0667 | 6 | 0.6559 | 0.1729 | 0.6559 | 0.8099 |
|
| 55 |
+
| No log | 0.0889 | 8 | 0.6892 | 0.3399 | 0.6892 | 0.8302 |
|
| 56 |
+
| No log | 0.1111 | 10 | 0.8610 | 0.3455 | 0.8610 | 0.9279 |
|
| 57 |
+
| No log | 0.1333 | 12 | 0.6850 | 0.4884 | 0.6850 | 0.8276 |
|
| 58 |
+
| No log | 0.1556 | 14 | 0.4917 | 0.5386 | 0.4917 | 0.7012 |
|
| 59 |
+
| No log | 0.1778 | 16 | 0.4163 | 0.6377 | 0.4163 | 0.6452 |
|
| 60 |
+
| No log | 0.2 | 18 | 0.4438 | 0.6181 | 0.4438 | 0.6662 |
|
| 61 |
+
| No log | 0.2222 | 20 | 0.7654 | 0.5309 | 0.7654 | 0.8749 |
|
| 62 |
+
| No log | 0.2444 | 22 | 0.7325 | 0.5309 | 0.7325 | 0.8559 |
|
| 63 |
+
| No log | 0.2667 | 24 | 0.4449 | 0.7317 | 0.4449 | 0.6670 |
|
| 64 |
+
| No log | 0.2889 | 26 | 0.4366 | 0.7606 | 0.4366 | 0.6608 |
|
| 65 |
+
| No log | 0.3111 | 28 | 0.6371 | 0.4815 | 0.6371 | 0.7982 |
|
| 66 |
+
| No log | 0.3333 | 30 | 0.8555 | 0.4969 | 0.8555 | 0.9249 |
|
| 67 |
+
| No log | 0.3556 | 32 | 0.6384 | 0.4937 | 0.6384 | 0.7990 |
|
| 68 |
+
| No log | 0.3778 | 34 | 0.3879 | 0.7032 | 0.3879 | 0.6228 |
|
| 69 |
+
| No log | 0.4 | 36 | 0.4004 | 0.6924 | 0.4004 | 0.6328 |
|
| 70 |
+
| No log | 0.4222 | 38 | 0.4167 | 0.6462 | 0.4167 | 0.6455 |
|
| 71 |
+
| No log | 0.4444 | 40 | 0.5291 | 0.5016 | 0.5291 | 0.7274 |
|
| 72 |
+
| No log | 0.4667 | 42 | 0.5077 | 0.4860 | 0.5077 | 0.7125 |
|
| 73 |
+
| No log | 0.4889 | 44 | 0.5378 | 0.5129 | 0.5378 | 0.7334 |
|
| 74 |
+
| No log | 0.5111 | 46 | 0.6631 | 0.4977 | 0.6631 | 0.8143 |
|
| 75 |
+
| No log | 0.5333 | 48 | 0.5395 | 0.5529 | 0.5395 | 0.7345 |
|
| 76 |
+
| No log | 0.5556 | 50 | 0.4447 | 0.7263 | 0.4447 | 0.6668 |
|
| 77 |
+
| No log | 0.5778 | 52 | 0.4697 | 0.6930 | 0.4697 | 0.6854 |
|
| 78 |
+
| No log | 0.6 | 54 | 0.4554 | 0.5943 | 0.4554 | 0.6749 |
|
| 79 |
+
| No log | 0.6222 | 56 | 0.6548 | 0.5295 | 0.6548 | 0.8092 |
|
| 80 |
+
| No log | 0.6444 | 58 | 0.7181 | 0.4977 | 0.7181 | 0.8474 |
|
| 81 |
+
| No log | 0.6667 | 60 | 0.5832 | 0.5265 | 0.5832 | 0.7637 |
|
| 82 |
+
| No log | 0.6889 | 62 | 0.4721 | 0.6325 | 0.4721 | 0.6871 |
|
| 83 |
+
| No log | 0.7111 | 64 | 0.5884 | 0.6221 | 0.5884 | 0.7671 |
|
| 84 |
+
| No log | 0.7333 | 66 | 0.5395 | 0.6392 | 0.5395 | 0.7345 |
|
| 85 |
+
| No log | 0.7556 | 68 | 0.5307 | 0.6557 | 0.5307 | 0.7285 |
|
| 86 |
+
| No log | 0.7778 | 70 | 0.5310 | 0.6360 | 0.5310 | 0.7287 |
|
| 87 |
+
| No log | 0.8 | 72 | 0.5161 | 0.6482 | 0.5161 | 0.7184 |
|
| 88 |
+
| No log | 0.8222 | 74 | 0.4745 | 0.6557 | 0.4745 | 0.6888 |
|
| 89 |
+
| No log | 0.8444 | 76 | 0.4562 | 0.6247 | 0.4562 | 0.6754 |
|
| 90 |
+
| No log | 0.8667 | 78 | 0.4972 | 0.5636 | 0.4972 | 0.7051 |
|
| 91 |
+
| No log | 0.8889 | 80 | 0.4424 | 0.6503 | 0.4424 | 0.6651 |
|
| 92 |
+
| No log | 0.9111 | 82 | 0.4427 | 0.6038 | 0.4427 | 0.6653 |
|
| 93 |
+
| No log | 0.9333 | 84 | 0.5762 | 0.5195 | 0.5762 | 0.7591 |
|
| 94 |
+
| No log | 0.9556 | 86 | 0.5385 | 0.5403 | 0.5385 | 0.7338 |
|
| 95 |
+
| No log | 0.9778 | 88 | 0.4221 | 0.6452 | 0.4221 | 0.6497 |
|
| 96 |
+
| No log | 1.0 | 90 | 0.6263 | 0.4650 | 0.6263 | 0.7914 |
|
| 97 |
+
| No log | 1.0222 | 92 | 0.7027 | 0.3867 | 0.7027 | 0.8383 |
|
| 98 |
+
| No log | 1.0444 | 94 | 0.5759 | 0.5018 | 0.5759 | 0.7589 |
|
| 99 |
+
| No log | 1.0667 | 96 | 0.5071 | 0.6092 | 0.5071 | 0.7121 |
|
| 100 |
+
| No log | 1.0889 | 98 | 0.4915 | 0.6277 | 0.4915 | 0.7010 |
|
| 101 |
+
| No log | 1.1111 | 100 | 0.5221 | 0.5556 | 0.5221 | 0.7226 |
|
| 102 |
+
| No log | 1.1333 | 102 | 0.5536 | 0.4957 | 0.5536 | 0.7440 |
|
| 103 |
+
| No log | 1.1556 | 104 | 0.5379 | 0.5575 | 0.5379 | 0.7334 |
|
| 104 |
+
| No log | 1.1778 | 106 | 0.5279 | 0.5538 | 0.5279 | 0.7265 |
|
| 105 |
+
| No log | 1.2 | 108 | 0.5695 | 0.5735 | 0.5695 | 0.7546 |
|
| 106 |
+
| No log | 1.2222 | 110 | 0.5345 | 0.6108 | 0.5345 | 0.7311 |
|
| 107 |
+
| No log | 1.2444 | 112 | 0.5283 | 0.6252 | 0.5283 | 0.7268 |
|
| 108 |
+
| No log | 1.2667 | 114 | 0.5366 | 0.6596 | 0.5366 | 0.7325 |
|
| 109 |
+
| No log | 1.2889 | 116 | 0.5256 | 0.6345 | 0.5256 | 0.7250 |
|
| 110 |
+
| No log | 1.3111 | 118 | 0.4968 | 0.6560 | 0.4968 | 0.7048 |
|
| 111 |
+
| No log | 1.3333 | 120 | 0.4700 | 0.6656 | 0.4700 | 0.6855 |
|
| 112 |
+
| No log | 1.3556 | 122 | 0.4520 | 0.7333 | 0.4520 | 0.6723 |
|
| 113 |
+
| No log | 1.3778 | 124 | 0.4408 | 0.6553 | 0.4408 | 0.6640 |
|
| 114 |
+
| No log | 1.4 | 126 | 0.4423 | 0.6806 | 0.4423 | 0.6650 |
|
| 115 |
+
| No log | 1.4222 | 128 | 0.4628 | 0.6694 | 0.4628 | 0.6803 |
|
| 116 |
+
| No log | 1.4444 | 130 | 0.4690 | 0.6609 | 0.4690 | 0.6848 |
|
| 117 |
+
| No log | 1.4667 | 132 | 0.4617 | 0.6284 | 0.4617 | 0.6795 |
|
| 118 |
+
| No log | 1.4889 | 134 | 0.5050 | 0.5748 | 0.5050 | 0.7106 |
|
| 119 |
+
| No log | 1.5111 | 136 | 0.4437 | 0.6639 | 0.4437 | 0.6661 |
|
| 120 |
+
| No log | 1.5333 | 138 | 0.4530 | 0.6020 | 0.4530 | 0.6731 |
|
| 121 |
+
| No log | 1.5556 | 140 | 0.5142 | 0.6442 | 0.5142 | 0.7171 |
|
| 122 |
+
| No log | 1.5778 | 142 | 0.5069 | 0.6709 | 0.5069 | 0.7119 |
|
| 123 |
+
| No log | 1.6 | 144 | 0.4707 | 0.6088 | 0.4707 | 0.6861 |
|
| 124 |
+
| No log | 1.6222 | 146 | 0.4852 | 0.6467 | 0.4852 | 0.6966 |
|
| 125 |
+
| No log | 1.6444 | 148 | 0.4644 | 0.6136 | 0.4644 | 0.6815 |
|
| 126 |
+
| No log | 1.6667 | 150 | 0.4729 | 0.6337 | 0.4729 | 0.6877 |
|
| 127 |
+
| No log | 1.6889 | 152 | 0.4727 | 0.6248 | 0.4727 | 0.6875 |
|
| 128 |
+
| No log | 1.7111 | 154 | 0.4213 | 0.6364 | 0.4213 | 0.6491 |
|
| 129 |
+
| No log | 1.7333 | 156 | 0.4129 | 0.6542 | 0.4129 | 0.6426 |
|
| 130 |
+
| No log | 1.7556 | 158 | 0.4516 | 0.6114 | 0.4516 | 0.6720 |
|
| 131 |
+
| No log | 1.7778 | 160 | 0.4835 | 0.6260 | 0.4835 | 0.6953 |
|
| 132 |
+
| No log | 1.8 | 162 | 0.4499 | 0.6514 | 0.4499 | 0.6707 |
|
| 133 |
+
| No log | 1.8222 | 164 | 0.4076 | 0.6087 | 0.4076 | 0.6385 |
|
| 134 |
+
| No log | 1.8444 | 166 | 0.4082 | 0.6632 | 0.4082 | 0.6389 |
|
| 135 |
+
| No log | 1.8667 | 168 | 0.4132 | 0.6467 | 0.4132 | 0.6428 |
|
| 136 |
+
| No log | 1.8889 | 170 | 0.5727 | 0.5489 | 0.5727 | 0.7568 |
|
| 137 |
+
| No log | 1.9111 | 172 | 0.6725 | 0.5667 | 0.6725 | 0.8200 |
|
| 138 |
+
| No log | 1.9333 | 174 | 0.5687 | 0.6379 | 0.5687 | 0.7541 |
|
| 139 |
+
| No log | 1.9556 | 176 | 0.5546 | 0.6060 | 0.5546 | 0.7447 |
|
| 140 |
+
| No log | 1.9778 | 178 | 0.5302 | 0.6118 | 0.5302 | 0.7281 |
|
| 141 |
+
| No log | 2.0 | 180 | 0.4649 | 0.6561 | 0.4649 | 0.6818 |
|
| 142 |
+
| No log | 2.0222 | 182 | 0.4887 | 0.6182 | 0.4887 | 0.6991 |
|
| 143 |
+
| No log | 2.0444 | 184 | 0.4916 | 0.6017 | 0.4916 | 0.7011 |
|
| 144 |
+
| No log | 2.0667 | 186 | 0.4845 | 0.6896 | 0.4845 | 0.6960 |
|
| 145 |
+
| No log | 2.0889 | 188 | 0.4405 | 0.6492 | 0.4405 | 0.6637 |
|
| 146 |
+
| No log | 2.1111 | 190 | 0.4329 | 0.6371 | 0.4329 | 0.6580 |
|
| 147 |
+
| No log | 2.1333 | 192 | 0.4495 | 0.6492 | 0.4495 | 0.6705 |
|
| 148 |
+
| No log | 2.1556 | 194 | 0.4493 | 0.6641 | 0.4493 | 0.6703 |
|
| 149 |
+
| No log | 2.1778 | 196 | 0.4436 | 0.6723 | 0.4436 | 0.6660 |
|
| 150 |
+
| No log | 2.2 | 198 | 0.4338 | 0.6014 | 0.4338 | 0.6586 |
|
| 151 |
+
| No log | 2.2222 | 200 | 0.4541 | 0.6419 | 0.4541 | 0.6739 |
|
| 152 |
+
| No log | 2.2444 | 202 | 0.4724 | 0.5970 | 0.4724 | 0.6873 |
|
| 153 |
+
| No log | 2.2667 | 204 | 0.4250 | 0.6455 | 0.4250 | 0.6519 |
|
| 154 |
+
| No log | 2.2889 | 206 | 0.4612 | 0.6604 | 0.4612 | 0.6791 |
|
| 155 |
+
| No log | 2.3111 | 208 | 0.5083 | 0.5775 | 0.5083 | 0.7129 |
|
| 156 |
+
| No log | 2.3333 | 210 | 0.4657 | 0.6337 | 0.4657 | 0.6824 |
|
| 157 |
+
| No log | 2.3556 | 212 | 0.4204 | 0.6736 | 0.4204 | 0.6484 |
|
| 158 |
+
| No log | 2.3778 | 214 | 0.4421 | 0.5406 | 0.4421 | 0.6649 |
|
| 159 |
+
| No log | 2.4 | 216 | 0.4648 | 0.5841 | 0.4648 | 0.6817 |
|
| 160 |
+
| No log | 2.4222 | 218 | 0.4303 | 0.6101 | 0.4303 | 0.6560 |
|
| 161 |
+
| No log | 2.4444 | 220 | 0.4260 | 0.6818 | 0.4260 | 0.6527 |
|
| 162 |
+
| No log | 2.4667 | 222 | 0.4279 | 0.6818 | 0.4279 | 0.6541 |
|
| 163 |
+
| No log | 2.4889 | 224 | 0.4282 | 0.5611 | 0.4282 | 0.6544 |
|
| 164 |
+
| No log | 2.5111 | 226 | 0.4884 | 0.5627 | 0.4884 | 0.6988 |
|
| 165 |
+
| No log | 2.5333 | 228 | 0.4587 | 0.5627 | 0.4587 | 0.6773 |
|
| 166 |
+
| No log | 2.5556 | 230 | 0.4210 | 0.6736 | 0.4210 | 0.6488 |
|
| 167 |
+
| No log | 2.5778 | 232 | 0.4930 | 0.6087 | 0.4930 | 0.7021 |
|
| 168 |
+
| No log | 2.6 | 234 | 0.4926 | 0.6394 | 0.4926 | 0.7019 |
|
| 169 |
+
| No log | 2.6222 | 236 | 0.4400 | 0.6908 | 0.4400 | 0.6634 |
|
| 170 |
+
| No log | 2.6444 | 238 | 0.4512 | 0.5826 | 0.4512 | 0.6717 |
|
| 171 |
+
| No log | 2.6667 | 240 | 0.6260 | 0.5934 | 0.6260 | 0.7912 |
|
| 172 |
+
| No log | 2.6889 | 242 | 0.7229 | 0.4859 | 0.7229 | 0.8503 |
|
| 173 |
+
| No log | 2.7111 | 244 | 0.6491 | 0.5850 | 0.6491 | 0.8057 |
|
| 174 |
+
| No log | 2.7333 | 246 | 0.5625 | 0.6046 | 0.5625 | 0.7500 |
|
| 175 |
+
| No log | 2.7556 | 248 | 0.5723 | 0.6305 | 0.5723 | 0.7565 |
|
| 176 |
+
| No log | 2.7778 | 250 | 0.5077 | 0.6529 | 0.5077 | 0.7125 |
|
| 177 |
+
| No log | 2.8 | 252 | 0.4439 | 0.6242 | 0.4439 | 0.6663 |
|
| 178 |
+
| No log | 2.8222 | 254 | 0.4474 | 0.5617 | 0.4474 | 0.6688 |
|
| 179 |
+
| No log | 2.8444 | 256 | 0.4623 | 0.4960 | 0.4623 | 0.6799 |
|
| 180 |
+
| No log | 2.8667 | 258 | 0.4439 | 0.5538 | 0.4439 | 0.6663 |
|
| 181 |
+
| No log | 2.8889 | 260 | 0.4278 | 0.6632 | 0.4278 | 0.6541 |
|
| 182 |
+
| No log | 2.9111 | 262 | 0.4398 | 0.6346 | 0.4398 | 0.6631 |
|
| 183 |
+
| No log | 2.9333 | 264 | 0.4487 | 0.5725 | 0.4487 | 0.6698 |
|
| 184 |
+
| No log | 2.9556 | 266 | 0.4510 | 0.5725 | 0.4510 | 0.6716 |
|
| 185 |
+
| No log | 2.9778 | 268 | 0.4506 | 0.6346 | 0.4506 | 0.6713 |
|
| 186 |
+
| No log | 3.0 | 270 | 0.4538 | 0.6632 | 0.4538 | 0.6737 |
|
| 187 |
+
| No log | 3.0222 | 272 | 0.4456 | 0.5446 | 0.4456 | 0.6676 |
|
| 188 |
+
| No log | 3.0444 | 274 | 0.4975 | 0.5627 | 0.4975 | 0.7053 |
|
| 189 |
+
| No log | 3.0667 | 276 | 0.4811 | 0.5627 | 0.4811 | 0.6936 |
|
| 190 |
+
| No log | 3.0889 | 278 | 0.4514 | 0.6632 | 0.4514 | 0.6719 |
|
| 191 |
+
| No log | 3.1111 | 280 | 0.5498 | 0.5812 | 0.5498 | 0.7415 |
|
| 192 |
+
| No log | 3.1333 | 282 | 0.6051 | 0.5739 | 0.6051 | 0.7779 |
|
| 193 |
+
| No log | 3.1556 | 284 | 0.5094 | 0.6188 | 0.5094 | 0.7137 |
|
| 194 |
+
| No log | 3.1778 | 286 | 0.4544 | 0.5672 | 0.4544 | 0.6741 |
|
| 195 |
+
| No log | 3.2 | 288 | 0.5188 | 0.5230 | 0.5188 | 0.7203 |
|
| 196 |
+
| No log | 3.2222 | 290 | 0.5195 | 0.4997 | 0.5195 | 0.7207 |
|
| 197 |
+
| No log | 3.2444 | 292 | 0.4714 | 0.5321 | 0.4714 | 0.6866 |
|
| 198 |
+
| No log | 3.2667 | 294 | 0.4596 | 0.6010 | 0.4596 | 0.6779 |
|
| 199 |
+
| No log | 3.2889 | 296 | 0.4608 | 0.6115 | 0.4608 | 0.6789 |
|
| 200 |
+
| No log | 3.3111 | 298 | 0.4462 | 0.6060 | 0.4462 | 0.6680 |
|
| 201 |
+
| No log | 3.3333 | 300 | 0.4861 | 0.6047 | 0.4861 | 0.6972 |
|
| 202 |
+
| No log | 3.3556 | 302 | 0.5039 | 0.6074 | 0.5039 | 0.7099 |
|
| 203 |
+
| No log | 3.3778 | 304 | 0.4654 | 0.5826 | 0.4654 | 0.6822 |
|
| 204 |
+
| No log | 3.4 | 306 | 0.4430 | 0.5956 | 0.4430 | 0.6656 |
|
| 205 |
+
| No log | 3.4222 | 308 | 0.4782 | 0.5115 | 0.4782 | 0.6915 |
|
| 206 |
+
| No log | 3.4444 | 310 | 0.5110 | 0.4948 | 0.5110 | 0.7148 |
|
| 207 |
+
| No log | 3.4667 | 312 | 0.4867 | 0.5184 | 0.4867 | 0.6977 |
|
| 208 |
+
| No log | 3.4889 | 314 | 0.4864 | 0.5617 | 0.4864 | 0.6974 |
|
| 209 |
+
| No log | 3.5111 | 316 | 0.4673 | 0.6038 | 0.4673 | 0.6836 |
|
| 210 |
+
| No log | 3.5333 | 318 | 0.4260 | 0.6242 | 0.4260 | 0.6527 |
|
| 211 |
+
| No log | 3.5556 | 320 | 0.4538 | 0.6330 | 0.4538 | 0.6736 |
|
| 212 |
+
| No log | 3.5778 | 322 | 0.5088 | 0.6273 | 0.5088 | 0.7133 |
|
| 213 |
+
| No log | 3.6 | 324 | 0.4930 | 0.6092 | 0.4930 | 0.7021 |
|
| 214 |
+
| No log | 3.6222 | 326 | 0.4695 | 0.6515 | 0.4695 | 0.6852 |
|
| 215 |
+
| No log | 3.6444 | 328 | 0.4591 | 0.6553 | 0.4591 | 0.6776 |
|
| 216 |
+
| No log | 3.6667 | 330 | 0.4950 | 0.6174 | 0.4950 | 0.7035 |
|
| 217 |
+
| No log | 3.6889 | 332 | 0.5160 | 0.5884 | 0.5160 | 0.7184 |
|
| 218 |
+
| No log | 3.7111 | 334 | 0.4924 | 0.6313 | 0.4924 | 0.7017 |
|
| 219 |
+
| No log | 3.7333 | 336 | 0.4730 | 0.5625 | 0.4730 | 0.6878 |
|
| 220 |
+
| No log | 3.7556 | 338 | 0.4746 | 0.5625 | 0.4746 | 0.6889 |
|
| 221 |
+
| No log | 3.7778 | 340 | 0.4710 | 0.6129 | 0.4710 | 0.6863 |
|
| 222 |
+
| No log | 3.8 | 342 | 0.4621 | 0.6620 | 0.4621 | 0.6798 |
|
| 223 |
+
| No log | 3.8222 | 344 | 0.4526 | 0.6142 | 0.4526 | 0.6727 |
|
| 224 |
+
| No log | 3.8444 | 346 | 0.4557 | 0.6530 | 0.4557 | 0.6751 |
|
| 225 |
+
| No log | 3.8667 | 348 | 0.4706 | 0.6145 | 0.4706 | 0.6860 |
|
| 226 |
+
| No log | 3.8889 | 350 | 0.4574 | 0.6073 | 0.4574 | 0.6763 |
|
| 227 |
+
| No log | 3.9111 | 352 | 0.4791 | 0.6431 | 0.4791 | 0.6922 |
|
| 228 |
+
| No log | 3.9333 | 354 | 0.4931 | 0.6061 | 0.4931 | 0.7022 |
|
| 229 |
+
| No log | 3.9556 | 356 | 0.4645 | 0.5248 | 0.4645 | 0.6815 |
|
| 230 |
+
| No log | 3.9778 | 358 | 0.4677 | 0.6820 | 0.4677 | 0.6839 |
|
| 231 |
+
| No log | 4.0 | 360 | 0.4917 | 0.5310 | 0.4917 | 0.7012 |
|
| 232 |
+
| No log | 4.0222 | 362 | 0.5019 | 0.5067 | 0.5019 | 0.7085 |
|
| 233 |
+
| No log | 4.0444 | 364 | 0.4871 | 0.6505 | 0.4871 | 0.6979 |
|
| 234 |
+
| No log | 4.0667 | 366 | 0.4626 | 0.6142 | 0.4626 | 0.6802 |
|
| 235 |
+
| No log | 4.0889 | 368 | 0.4611 | 0.5672 | 0.4611 | 0.6790 |
|
| 236 |
+
| No log | 4.1111 | 370 | 0.4715 | 0.5904 | 0.4715 | 0.6867 |
|
| 237 |
+
| No log | 4.1333 | 372 | 0.4709 | 0.5580 | 0.4709 | 0.6862 |
|
| 238 |
+
| No log | 4.1556 | 374 | 0.4746 | 0.5888 | 0.4746 | 0.6889 |
|
| 239 |
+
| No log | 4.1778 | 376 | 0.4696 | 0.5405 | 0.4696 | 0.6853 |
|
| 240 |
+
| No log | 4.2 | 378 | 0.4650 | 0.5373 | 0.4650 | 0.6819 |
|
| 241 |
+
| No log | 4.2222 | 380 | 0.4689 | 0.6129 | 0.4689 | 0.6848 |
|
| 242 |
+
| No log | 4.2444 | 382 | 0.4769 | 0.6313 | 0.4769 | 0.6906 |
|
| 243 |
+
| No log | 4.2667 | 384 | 0.4696 | 0.6624 | 0.4696 | 0.6853 |
|
| 244 |
+
| No log | 4.2889 | 386 | 0.4571 | 0.6215 | 0.4571 | 0.6761 |
|
| 245 |
+
| No log | 4.3111 | 388 | 0.4631 | 0.5321 | 0.4631 | 0.6805 |
|
| 246 |
+
| No log | 4.3333 | 390 | 0.4916 | 0.5212 | 0.4916 | 0.7011 |
|
| 247 |
+
| No log | 4.3556 | 392 | 0.4830 | 0.5642 | 0.4830 | 0.6949 |
|
| 248 |
+
| No log | 4.3778 | 394 | 0.4457 | 0.5446 | 0.4457 | 0.6676 |
|
| 249 |
+
| No log | 4.4 | 396 | 0.4506 | 0.6908 | 0.4506 | 0.6712 |
|
| 250 |
+
| No log | 4.4222 | 398 | 0.4407 | 0.6908 | 0.4407 | 0.6639 |
|
| 251 |
+
| No log | 4.4444 | 400 | 0.4463 | 0.5611 | 0.4463 | 0.6680 |
|
| 252 |
+
| No log | 4.4667 | 402 | 0.4787 | 0.5794 | 0.4787 | 0.6918 |
|
| 253 |
+
| No log | 4.4889 | 404 | 0.4644 | 0.5569 | 0.4644 | 0.6815 |
|
| 254 |
+
| No log | 4.5111 | 406 | 0.4282 | 0.5304 | 0.4282 | 0.6544 |
|
| 255 |
+
| No log | 4.5333 | 408 | 0.4232 | 0.7208 | 0.4232 | 0.6505 |
|
| 256 |
+
| No log | 4.5556 | 410 | 0.4323 | 0.6702 | 0.4323 | 0.6575 |
|
| 257 |
+
| No log | 4.5778 | 412 | 0.4245 | 0.6830 | 0.4245 | 0.6515 |
|
| 258 |
+
| No log | 4.6 | 414 | 0.4553 | 0.6079 | 0.4553 | 0.6748 |
|
| 259 |
+
| No log | 4.6222 | 416 | 0.4970 | 0.6181 | 0.4970 | 0.7050 |
|
| 260 |
+
| No log | 4.6444 | 418 | 0.4802 | 0.6181 | 0.4802 | 0.6930 |
|
| 261 |
+
| No log | 4.6667 | 420 | 0.4684 | 0.5983 | 0.4684 | 0.6844 |
|
| 262 |
+
| No log | 4.6889 | 422 | 0.4305 | 0.5373 | 0.4305 | 0.6561 |
|
| 263 |
+
| No log | 4.7111 | 424 | 0.4231 | 0.5681 | 0.4231 | 0.6505 |
|
| 264 |
+
| No log | 4.7333 | 426 | 0.4286 | 0.5681 | 0.4286 | 0.6547 |
|
| 265 |
+
| No log | 4.7556 | 428 | 0.4340 | 0.5304 | 0.4340 | 0.6588 |
|
| 266 |
+
| No log | 4.7778 | 430 | 0.4340 | 0.5390 | 0.4340 | 0.6588 |
|
| 267 |
+
| No log | 4.8 | 432 | 0.4356 | 0.5797 | 0.4356 | 0.6600 |
|
| 268 |
+
| No log | 4.8222 | 434 | 0.4441 | 0.6007 | 0.4441 | 0.6664 |
|
| 269 |
+
| No log | 4.8444 | 436 | 0.4478 | 0.6289 | 0.4478 | 0.6692 |
|
| 270 |
+
| No log | 4.8667 | 438 | 0.4461 | 0.6741 | 0.4461 | 0.6679 |
|
| 271 |
+
| No log | 4.8889 | 440 | 0.4669 | 0.6418 | 0.4669 | 0.6833 |
|
| 272 |
+
| No log | 4.9111 | 442 | 0.4990 | 0.6025 | 0.4990 | 0.7064 |
|
| 273 |
+
| No log | 4.9333 | 444 | 0.4918 | 0.6406 | 0.4918 | 0.7013 |
|
| 274 |
+
| No log | 4.9556 | 446 | 0.4558 | 0.6506 | 0.4558 | 0.6751 |
|
| 275 |
+
| No log | 4.9778 | 448 | 0.4320 | 0.6820 | 0.4320 | 0.6572 |
|
| 276 |
+
| No log | 5.0 | 450 | 0.4250 | 0.6724 | 0.4250 | 0.6519 |
|
| 277 |
+
| No log | 5.0222 | 452 | 0.4193 | 0.6724 | 0.4193 | 0.6475 |
|
| 278 |
+
| No log | 5.0444 | 454 | 0.4256 | 0.6724 | 0.4256 | 0.6524 |
|
| 279 |
+
| No log | 5.0667 | 456 | 0.4224 | 0.6228 | 0.4224 | 0.6499 |
|
| 280 |
+
| No log | 5.0889 | 458 | 0.4193 | 0.6142 | 0.4193 | 0.6476 |
|
| 281 |
+
| No log | 5.1111 | 460 | 0.4440 | 0.7170 | 0.4440 | 0.6663 |
|
| 282 |
+
| No log | 5.1333 | 462 | 0.4920 | 0.6687 | 0.4920 | 0.7014 |
|
| 283 |
+
| No log | 5.1556 | 464 | 0.4921 | 0.6775 | 0.4921 | 0.7015 |
|
| 284 |
+
| No log | 5.1778 | 466 | 0.4606 | 0.7170 | 0.4606 | 0.6787 |
|
| 285 |
+
| No log | 5.2 | 468 | 0.4371 | 0.6443 | 0.4371 | 0.6612 |
|
| 286 |
+
| No log | 5.2222 | 470 | 0.4316 | 0.6267 | 0.4316 | 0.6570 |
|
| 287 |
+
| No log | 5.2444 | 472 | 0.4239 | 0.6739 | 0.4239 | 0.6510 |
|
| 288 |
+
| No log | 5.2667 | 474 | 0.4349 | 0.6530 | 0.4349 | 0.6595 |
|
| 289 |
+
| No log | 5.2889 | 476 | 0.4681 | 0.6776 | 0.4681 | 0.6842 |
|
| 290 |
+
| No log | 5.3111 | 478 | 0.4574 | 0.6601 | 0.4574 | 0.6763 |
|
| 291 |
+
| No log | 5.3333 | 480 | 0.4246 | 0.6898 | 0.4246 | 0.6516 |
|
| 292 |
+
| No log | 5.3556 | 482 | 0.4028 | 0.6542 | 0.4028 | 0.6347 |
|
| 293 |
+
| No log | 5.3778 | 484 | 0.4060 | 0.6364 | 0.4060 | 0.6372 |
|
| 294 |
+
| No log | 5.4 | 486 | 0.4030 | 0.6242 | 0.4030 | 0.6348 |
|
| 295 |
+
| No log | 5.4222 | 488 | 0.4014 | 0.6242 | 0.4014 | 0.6335 |
|
| 296 |
+
| No log | 5.4444 | 490 | 0.4089 | 0.7098 | 0.4089 | 0.6395 |
|
| 297 |
+
| No log | 5.4667 | 492 | 0.4180 | 0.7011 | 0.4180 | 0.6465 |
|
| 298 |
+
| No log | 5.4889 | 494 | 0.4192 | 0.5986 | 0.4192 | 0.6475 |
|
| 299 |
+
| No log | 5.5111 | 496 | 0.4431 | 0.5246 | 0.4431 | 0.6657 |
|
| 300 |
+
| No log | 5.5333 | 498 | 0.4524 | 0.5414 | 0.4524 | 0.6726 |
|
| 301 |
+
| 0.2943 | 5.5556 | 500 | 0.4452 | 0.5765 | 0.4452 | 0.6672 |
|
| 302 |
+
| 0.2943 | 5.5778 | 502 | 0.4639 | 0.5923 | 0.4639 | 0.6811 |
|
| 303 |
+
| 0.2943 | 5.6 | 504 | 0.4729 | 0.5945 | 0.4729 | 0.6877 |
|
| 304 |
+
| 0.2943 | 5.6222 | 506 | 0.4622 | 0.6053 | 0.4622 | 0.6798 |
|
| 305 |
+
| 0.2943 | 5.6444 | 508 | 0.4929 | 0.5455 | 0.4929 | 0.7021 |
|
| 306 |
+
| 0.2943 | 5.6667 | 510 | 0.5986 | 0.5363 | 0.5986 | 0.7737 |
|
| 307 |
+
| 0.2943 | 5.6889 | 512 | 0.5934 | 0.5146 | 0.5934 | 0.7703 |
|
| 308 |
+
| 0.2943 | 5.7111 | 514 | 0.5074 | 0.5603 | 0.5074 | 0.7123 |
|
| 309 |
+
| 0.2943 | 5.7333 | 516 | 0.4551 | 0.5324 | 0.4551 | 0.6746 |
|
| 310 |
+
|
| 311 |
+
|
| 312 |
+
### Framework versions
|
| 313 |
+
|
| 314 |
+
- Transformers 4.44.2
|
| 315 |
+
- Pytorch 2.4.0+cu118
|
| 316 |
+
- Datasets 2.21.0
|
| 317 |
+
- 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:b4f3d9be9014a6349d17673e6fbd39bb0fef32d9b2cd7d22bd684ab9a328126e
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e85db2e1f93e2f64fb5376021199a63295fd81988fa0f0241b97c8f4c27dc7b7
|
| 3 |
+
size 5304
|