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_OSS_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k18_task5_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_k18_task5_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: 0.6955
|
| 19 |
+
- Qwk: 0.5541
|
| 20 |
+
- Mse: 0.6955
|
| 21 |
+
- Rmse: 0.8339
|
| 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 | 4.1398 | 0.0130 | 4.1398 | 2.0346 |
|
| 53 |
+
| No log | 0.0444 | 4 | 2.3525 | 0.0458 | 2.3525 | 1.5338 |
|
| 54 |
+
| No log | 0.0667 | 6 | 1.5084 | -0.0457 | 1.5084 | 1.2282 |
|
| 55 |
+
| No log | 0.0889 | 8 | 1.3266 | -0.0695 | 1.3266 | 1.1518 |
|
| 56 |
+
| No log | 0.1111 | 10 | 2.0830 | 0.0709 | 2.0830 | 1.4433 |
|
| 57 |
+
| No log | 0.1333 | 12 | 2.4225 | 0.0618 | 2.4225 | 1.5564 |
|
| 58 |
+
| No log | 0.1556 | 14 | 1.7524 | 0.2137 | 1.7524 | 1.3238 |
|
| 59 |
+
| No log | 0.1778 | 16 | 0.8995 | 0.3776 | 0.8995 | 0.9484 |
|
| 60 |
+
| No log | 0.2 | 18 | 0.8415 | 0.3360 | 0.8415 | 0.9173 |
|
| 61 |
+
| No log | 0.2222 | 20 | 0.8698 | 0.2849 | 0.8698 | 0.9327 |
|
| 62 |
+
| No log | 0.2444 | 22 | 0.8543 | 0.3001 | 0.8543 | 0.9243 |
|
| 63 |
+
| No log | 0.2667 | 24 | 0.8116 | 0.3961 | 0.8116 | 0.9009 |
|
| 64 |
+
| No log | 0.2889 | 26 | 0.9272 | 0.3793 | 0.9272 | 0.9629 |
|
| 65 |
+
| No log | 0.3111 | 28 | 0.9571 | 0.3919 | 0.9571 | 0.9783 |
|
| 66 |
+
| No log | 0.3333 | 30 | 1.1281 | 0.375 | 1.1281 | 1.0621 |
|
| 67 |
+
| No log | 0.3556 | 32 | 1.3072 | 0.4079 | 1.3072 | 1.1433 |
|
| 68 |
+
| No log | 0.3778 | 34 | 0.9727 | 0.4053 | 0.9727 | 0.9863 |
|
| 69 |
+
| No log | 0.4 | 36 | 0.9531 | 0.4574 | 0.9531 | 0.9763 |
|
| 70 |
+
| No log | 0.4222 | 38 | 1.3637 | 0.3511 | 1.3637 | 1.1678 |
|
| 71 |
+
| No log | 0.4444 | 40 | 1.4513 | 0.3261 | 1.4513 | 1.2047 |
|
| 72 |
+
| No log | 0.4667 | 42 | 0.9842 | 0.5376 | 0.9842 | 0.9920 |
|
| 73 |
+
| No log | 0.4889 | 44 | 0.7493 | 0.5979 | 0.7493 | 0.8656 |
|
| 74 |
+
| No log | 0.5111 | 46 | 0.8381 | 0.6255 | 0.8381 | 0.9155 |
|
| 75 |
+
| No log | 0.5333 | 48 | 1.1957 | 0.4455 | 1.1957 | 1.0935 |
|
| 76 |
+
| No log | 0.5556 | 50 | 1.1459 | 0.4688 | 1.1459 | 1.0705 |
|
| 77 |
+
| No log | 0.5778 | 52 | 0.9064 | 0.6128 | 0.9064 | 0.9520 |
|
| 78 |
+
| No log | 0.6 | 54 | 0.7538 | 0.6602 | 0.7538 | 0.8682 |
|
| 79 |
+
| No log | 0.6222 | 56 | 0.7585 | 0.6384 | 0.7585 | 0.8709 |
|
| 80 |
+
| No log | 0.6444 | 58 | 0.7896 | 0.6369 | 0.7896 | 0.8886 |
|
| 81 |
+
| No log | 0.6667 | 60 | 0.7837 | 0.6188 | 0.7837 | 0.8853 |
|
| 82 |
+
| No log | 0.6889 | 62 | 0.7466 | 0.6412 | 0.7466 | 0.8641 |
|
| 83 |
+
| No log | 0.7111 | 64 | 0.7678 | 0.6202 | 0.7678 | 0.8763 |
|
| 84 |
+
| No log | 0.7333 | 66 | 0.8969 | 0.6322 | 0.8969 | 0.9471 |
|
| 85 |
+
| No log | 0.7556 | 68 | 0.7901 | 0.6264 | 0.7901 | 0.8889 |
|
| 86 |
+
| No log | 0.7778 | 70 | 0.8272 | 0.6516 | 0.8272 | 0.9095 |
|
| 87 |
+
| No log | 0.8 | 72 | 1.0201 | 0.5690 | 1.0201 | 1.0100 |
|
| 88 |
+
| No log | 0.8222 | 74 | 0.8797 | 0.6061 | 0.8797 | 0.9379 |
|
| 89 |
+
| No log | 0.8444 | 76 | 0.7088 | 0.5835 | 0.7088 | 0.8419 |
|
| 90 |
+
| No log | 0.8667 | 78 | 0.7069 | 0.6382 | 0.7069 | 0.8408 |
|
| 91 |
+
| No log | 0.8889 | 80 | 0.7209 | 0.6403 | 0.7209 | 0.8490 |
|
| 92 |
+
| No log | 0.9111 | 82 | 0.6601 | 0.6411 | 0.6601 | 0.8125 |
|
| 93 |
+
| No log | 0.9333 | 84 | 0.6473 | 0.6328 | 0.6473 | 0.8046 |
|
| 94 |
+
| No log | 0.9556 | 86 | 0.7222 | 0.6035 | 0.7222 | 0.8498 |
|
| 95 |
+
| No log | 0.9778 | 88 | 0.8216 | 0.5749 | 0.8216 | 0.9064 |
|
| 96 |
+
| No log | 1.0 | 90 | 0.7764 | 0.5564 | 0.7764 | 0.8811 |
|
| 97 |
+
| No log | 1.0222 | 92 | 0.8798 | 0.6370 | 0.8798 | 0.9380 |
|
| 98 |
+
| No log | 1.0444 | 94 | 1.0081 | 0.5873 | 1.0081 | 1.0040 |
|
| 99 |
+
| No log | 1.0667 | 96 | 0.8703 | 0.6075 | 0.8703 | 0.9329 |
|
| 100 |
+
| No log | 1.0889 | 98 | 0.8161 | 0.5620 | 0.8161 | 0.9034 |
|
| 101 |
+
| No log | 1.1111 | 100 | 1.0445 | 0.4643 | 1.0445 | 1.0220 |
|
| 102 |
+
| No log | 1.1333 | 102 | 0.9518 | 0.4905 | 0.9518 | 0.9756 |
|
| 103 |
+
| No log | 1.1556 | 104 | 0.8900 | 0.5350 | 0.8900 | 0.9434 |
|
| 104 |
+
| No log | 1.1778 | 106 | 0.7363 | 0.6063 | 0.7363 | 0.8581 |
|
| 105 |
+
| No log | 1.2 | 108 | 0.6991 | 0.6176 | 0.6991 | 0.8361 |
|
| 106 |
+
| No log | 1.2222 | 110 | 0.6769 | 0.6543 | 0.6769 | 0.8227 |
|
| 107 |
+
| No log | 1.2444 | 112 | 0.6478 | 0.6789 | 0.6478 | 0.8049 |
|
| 108 |
+
| No log | 1.2667 | 114 | 0.6286 | 0.6622 | 0.6286 | 0.7928 |
|
| 109 |
+
| No log | 1.2889 | 116 | 0.6189 | 0.6444 | 0.6189 | 0.7867 |
|
| 110 |
+
| No log | 1.3111 | 118 | 0.6170 | 0.6636 | 0.6170 | 0.7855 |
|
| 111 |
+
| No log | 1.3333 | 120 | 0.6370 | 0.6630 | 0.6370 | 0.7981 |
|
| 112 |
+
| No log | 1.3556 | 122 | 0.7052 | 0.6492 | 0.7052 | 0.8398 |
|
| 113 |
+
| No log | 1.3778 | 124 | 0.7420 | 0.6555 | 0.7420 | 0.8614 |
|
| 114 |
+
| No log | 1.4 | 126 | 0.7075 | 0.6706 | 0.7075 | 0.8411 |
|
| 115 |
+
| No log | 1.4222 | 128 | 0.6794 | 0.6568 | 0.6794 | 0.8242 |
|
| 116 |
+
| No log | 1.4444 | 130 | 0.7155 | 0.6396 | 0.7155 | 0.8459 |
|
| 117 |
+
| No log | 1.4667 | 132 | 0.7974 | 0.5536 | 0.7974 | 0.8930 |
|
| 118 |
+
| No log | 1.4889 | 134 | 0.7802 | 0.5359 | 0.7802 | 0.8833 |
|
| 119 |
+
| No log | 1.5111 | 136 | 0.6821 | 0.5830 | 0.6821 | 0.8259 |
|
| 120 |
+
| No log | 1.5333 | 138 | 0.7016 | 0.6148 | 0.7016 | 0.8376 |
|
| 121 |
+
| No log | 1.5556 | 140 | 0.8073 | 0.5574 | 0.8073 | 0.8985 |
|
| 122 |
+
| No log | 1.5778 | 142 | 1.0499 | 0.5505 | 1.0499 | 1.0247 |
|
| 123 |
+
| No log | 1.6 | 144 | 1.0556 | 0.5341 | 1.0556 | 1.0274 |
|
| 124 |
+
| No log | 1.6222 | 146 | 0.8334 | 0.5964 | 0.8334 | 0.9129 |
|
| 125 |
+
| No log | 1.6444 | 148 | 0.7358 | 0.6087 | 0.7358 | 0.8578 |
|
| 126 |
+
| No log | 1.6667 | 150 | 0.7060 | 0.6169 | 0.7060 | 0.8402 |
|
| 127 |
+
| No log | 1.6889 | 152 | 0.7040 | 0.6205 | 0.7040 | 0.8390 |
|
| 128 |
+
| No log | 1.7111 | 154 | 0.7093 | 0.6664 | 0.7093 | 0.8422 |
|
| 129 |
+
| No log | 1.7333 | 156 | 0.7376 | 0.6105 | 0.7376 | 0.8589 |
|
| 130 |
+
| No log | 1.7556 | 158 | 0.7629 | 0.5760 | 0.7629 | 0.8734 |
|
| 131 |
+
| No log | 1.7778 | 160 | 0.6822 | 0.6278 | 0.6822 | 0.8260 |
|
| 132 |
+
| No log | 1.8 | 162 | 0.6948 | 0.4874 | 0.6948 | 0.8336 |
|
| 133 |
+
| No log | 1.8222 | 164 | 0.7088 | 0.5737 | 0.7088 | 0.8419 |
|
| 134 |
+
| No log | 1.8444 | 166 | 0.7409 | 0.5999 | 0.7409 | 0.8608 |
|
| 135 |
+
| No log | 1.8667 | 168 | 0.7947 | 0.6134 | 0.7947 | 0.8914 |
|
| 136 |
+
| No log | 1.8889 | 170 | 0.8402 | 0.6336 | 0.8402 | 0.9166 |
|
| 137 |
+
| No log | 1.9111 | 172 | 0.9772 | 0.5455 | 0.9772 | 0.9885 |
|
| 138 |
+
| No log | 1.9333 | 174 | 0.9536 | 0.5155 | 0.9536 | 0.9765 |
|
| 139 |
+
| No log | 1.9556 | 176 | 0.7895 | 0.5772 | 0.7895 | 0.8885 |
|
| 140 |
+
| No log | 1.9778 | 178 | 0.7687 | 0.5709 | 0.7687 | 0.8768 |
|
| 141 |
+
| No log | 2.0 | 180 | 0.8661 | 0.5607 | 0.8661 | 0.9306 |
|
| 142 |
+
| No log | 2.0222 | 182 | 0.8385 | 0.5327 | 0.8385 | 0.9157 |
|
| 143 |
+
| No log | 2.0444 | 184 | 0.7522 | 0.5329 | 0.7522 | 0.8673 |
|
| 144 |
+
| No log | 2.0667 | 186 | 0.6930 | 0.6460 | 0.6930 | 0.8325 |
|
| 145 |
+
| No log | 2.0889 | 188 | 0.7108 | 0.5902 | 0.7108 | 0.8431 |
|
| 146 |
+
| No log | 2.1111 | 190 | 0.7402 | 0.6032 | 0.7402 | 0.8603 |
|
| 147 |
+
| No log | 2.1333 | 192 | 0.7540 | 0.6379 | 0.7540 | 0.8683 |
|
| 148 |
+
| No log | 2.1556 | 194 | 0.7703 | 0.6214 | 0.7703 | 0.8777 |
|
| 149 |
+
| No log | 2.1778 | 196 | 0.7653 | 0.5757 | 0.7653 | 0.8748 |
|
| 150 |
+
| No log | 2.2 | 198 | 0.7556 | 0.6168 | 0.7556 | 0.8693 |
|
| 151 |
+
| No log | 2.2222 | 200 | 0.7574 | 0.6388 | 0.7574 | 0.8703 |
|
| 152 |
+
| No log | 2.2444 | 202 | 0.8013 | 0.6131 | 0.8013 | 0.8952 |
|
| 153 |
+
| No log | 2.2667 | 204 | 0.7792 | 0.5988 | 0.7792 | 0.8827 |
|
| 154 |
+
| No log | 2.2889 | 206 | 0.7154 | 0.5534 | 0.7154 | 0.8458 |
|
| 155 |
+
| No log | 2.3111 | 208 | 0.7309 | 0.6044 | 0.7309 | 0.8550 |
|
| 156 |
+
| No log | 2.3333 | 210 | 0.7449 | 0.6044 | 0.7449 | 0.8631 |
|
| 157 |
+
| No log | 2.3556 | 212 | 0.7227 | 0.5140 | 0.7227 | 0.8501 |
|
| 158 |
+
| No log | 2.3778 | 214 | 0.7364 | 0.5911 | 0.7364 | 0.8582 |
|
| 159 |
+
| No log | 2.4 | 216 | 0.7531 | 0.6502 | 0.7531 | 0.8678 |
|
| 160 |
+
| No log | 2.4222 | 218 | 0.7599 | 0.6655 | 0.7599 | 0.8717 |
|
| 161 |
+
| No log | 2.4444 | 220 | 0.7347 | 0.6502 | 0.7347 | 0.8571 |
|
| 162 |
+
| No log | 2.4667 | 222 | 0.7116 | 0.5508 | 0.7116 | 0.8435 |
|
| 163 |
+
| No log | 2.4889 | 224 | 0.7082 | 0.5508 | 0.7082 | 0.8415 |
|
| 164 |
+
| No log | 2.5111 | 226 | 0.7132 | 0.6293 | 0.7132 | 0.8445 |
|
| 165 |
+
| No log | 2.5333 | 228 | 0.6740 | 0.6868 | 0.6740 | 0.8210 |
|
| 166 |
+
| No log | 2.5556 | 230 | 0.6374 | 0.6493 | 0.6374 | 0.7984 |
|
| 167 |
+
| No log | 2.5778 | 232 | 0.6255 | 0.7064 | 0.6255 | 0.7909 |
|
| 168 |
+
| No log | 2.6 | 234 | 0.5992 | 0.6813 | 0.5992 | 0.7741 |
|
| 169 |
+
| No log | 2.6222 | 236 | 0.5979 | 0.6536 | 0.5979 | 0.7732 |
|
| 170 |
+
| No log | 2.6444 | 238 | 0.5935 | 0.6709 | 0.5935 | 0.7704 |
|
| 171 |
+
| No log | 2.6667 | 240 | 0.5998 | 0.6709 | 0.5998 | 0.7744 |
|
| 172 |
+
| No log | 2.6889 | 242 | 0.6036 | 0.6553 | 0.6036 | 0.7769 |
|
| 173 |
+
| No log | 2.7111 | 244 | 0.6391 | 0.6846 | 0.6391 | 0.7994 |
|
| 174 |
+
| No log | 2.7333 | 246 | 0.6672 | 0.6368 | 0.6672 | 0.8168 |
|
| 175 |
+
| No log | 2.7556 | 248 | 0.7055 | 0.6070 | 0.7055 | 0.8399 |
|
| 176 |
+
| No log | 2.7778 | 250 | 0.7950 | 0.5621 | 0.7950 | 0.8917 |
|
| 177 |
+
| No log | 2.8 | 252 | 0.8469 | 0.5496 | 0.8469 | 0.9203 |
|
| 178 |
+
| No log | 2.8222 | 254 | 0.8259 | 0.5591 | 0.8259 | 0.9088 |
|
| 179 |
+
| No log | 2.8444 | 256 | 0.7961 | 0.6317 | 0.7961 | 0.8922 |
|
| 180 |
+
| No log | 2.8667 | 258 | 0.7341 | 0.6053 | 0.7341 | 0.8568 |
|
| 181 |
+
| No log | 2.8889 | 260 | 0.6814 | 0.6226 | 0.6814 | 0.8255 |
|
| 182 |
+
| No log | 2.9111 | 262 | 0.6586 | 0.6536 | 0.6586 | 0.8115 |
|
| 183 |
+
| No log | 2.9333 | 264 | 0.6423 | 0.6581 | 0.6423 | 0.8014 |
|
| 184 |
+
| No log | 2.9556 | 266 | 0.6378 | 0.6605 | 0.6378 | 0.7986 |
|
| 185 |
+
| No log | 2.9778 | 268 | 0.6261 | 0.6709 | 0.6261 | 0.7913 |
|
| 186 |
+
| No log | 3.0 | 270 | 0.6175 | 0.6545 | 0.6175 | 0.7858 |
|
| 187 |
+
| No log | 3.0222 | 272 | 0.6383 | 0.6626 | 0.6383 | 0.7989 |
|
| 188 |
+
| No log | 3.0444 | 274 | 0.6744 | 0.6018 | 0.6744 | 0.8212 |
|
| 189 |
+
| No log | 3.0667 | 276 | 0.6516 | 0.6128 | 0.6516 | 0.8072 |
|
| 190 |
+
| No log | 3.0889 | 278 | 0.6120 | 0.6345 | 0.6120 | 0.7823 |
|
| 191 |
+
| No log | 3.1111 | 280 | 0.6021 | 0.6470 | 0.6021 | 0.7760 |
|
| 192 |
+
| No log | 3.1333 | 282 | 0.6068 | 0.6572 | 0.6068 | 0.7790 |
|
| 193 |
+
| No log | 3.1556 | 284 | 0.6427 | 0.6709 | 0.6427 | 0.8017 |
|
| 194 |
+
| No log | 3.1778 | 286 | 0.6973 | 0.6535 | 0.6973 | 0.8351 |
|
| 195 |
+
| No log | 3.2 | 288 | 0.7003 | 0.6322 | 0.7003 | 0.8369 |
|
| 196 |
+
| No log | 3.2222 | 290 | 0.6896 | 0.5889 | 0.6896 | 0.8304 |
|
| 197 |
+
| No log | 3.2444 | 292 | 0.7025 | 0.5775 | 0.7025 | 0.8381 |
|
| 198 |
+
| No log | 3.2667 | 294 | 0.7002 | 0.6699 | 0.7002 | 0.8368 |
|
| 199 |
+
| No log | 3.2889 | 296 | 0.6841 | 0.6673 | 0.6841 | 0.8271 |
|
| 200 |
+
| No log | 3.3111 | 298 | 0.6798 | 0.6699 | 0.6798 | 0.8245 |
|
| 201 |
+
| No log | 3.3333 | 300 | 0.6938 | 0.5958 | 0.6938 | 0.8330 |
|
| 202 |
+
| No log | 3.3556 | 302 | 0.7510 | 0.6340 | 0.7510 | 0.8666 |
|
| 203 |
+
| No log | 3.3778 | 304 | 0.7070 | 0.5919 | 0.7070 | 0.8408 |
|
| 204 |
+
| No log | 3.4 | 306 | 0.6658 | 0.5969 | 0.6658 | 0.8160 |
|
| 205 |
+
| No log | 3.4222 | 308 | 0.6528 | 0.6464 | 0.6528 | 0.8079 |
|
| 206 |
+
| No log | 3.4444 | 310 | 0.6508 | 0.6298 | 0.6508 | 0.8068 |
|
| 207 |
+
| No log | 3.4667 | 312 | 0.6466 | 0.6549 | 0.6466 | 0.8041 |
|
| 208 |
+
| No log | 3.4889 | 314 | 0.6636 | 0.6623 | 0.6636 | 0.8146 |
|
| 209 |
+
| No log | 3.5111 | 316 | 0.6743 | 0.6599 | 0.6743 | 0.8212 |
|
| 210 |
+
| No log | 3.5333 | 318 | 0.6626 | 0.6503 | 0.6626 | 0.8140 |
|
| 211 |
+
| No log | 3.5556 | 320 | 0.6584 | 0.6503 | 0.6584 | 0.8114 |
|
| 212 |
+
| No log | 3.5778 | 322 | 0.6618 | 0.6637 | 0.6618 | 0.8135 |
|
| 213 |
+
| No log | 3.6 | 324 | 0.6459 | 0.6423 | 0.6459 | 0.8037 |
|
| 214 |
+
| No log | 3.6222 | 326 | 0.6114 | 0.6955 | 0.6114 | 0.7819 |
|
| 215 |
+
| No log | 3.6444 | 328 | 0.6075 | 0.6470 | 0.6075 | 0.7794 |
|
| 216 |
+
| No log | 3.6667 | 330 | 0.5978 | 0.7224 | 0.5978 | 0.7732 |
|
| 217 |
+
| No log | 3.6889 | 332 | 0.6220 | 0.6714 | 0.6220 | 0.7887 |
|
| 218 |
+
| No log | 3.7111 | 334 | 0.6524 | 0.6379 | 0.6524 | 0.8077 |
|
| 219 |
+
| No log | 3.7333 | 336 | 0.6828 | 0.6527 | 0.6828 | 0.8263 |
|
| 220 |
+
| No log | 3.7556 | 338 | 0.6846 | 0.6179 | 0.6846 | 0.8274 |
|
| 221 |
+
| No log | 3.7778 | 340 | 0.6597 | 0.6261 | 0.6597 | 0.8122 |
|
| 222 |
+
| No log | 3.8 | 342 | 0.6743 | 0.6781 | 0.6743 | 0.8211 |
|
| 223 |
+
| No log | 3.8222 | 344 | 0.7062 | 0.6148 | 0.7062 | 0.8404 |
|
| 224 |
+
| No log | 3.8444 | 346 | 0.7647 | 0.6061 | 0.7647 | 0.8745 |
|
| 225 |
+
| No log | 3.8667 | 348 | 0.7119 | 0.6328 | 0.7119 | 0.8438 |
|
| 226 |
+
| No log | 3.8889 | 350 | 0.6759 | 0.6789 | 0.6759 | 0.8222 |
|
| 227 |
+
| No log | 3.9111 | 352 | 0.7181 | 0.6129 | 0.7181 | 0.8474 |
|
| 228 |
+
| No log | 3.9333 | 354 | 0.7892 | 0.6294 | 0.7892 | 0.8883 |
|
| 229 |
+
| No log | 3.9556 | 356 | 0.7363 | 0.6197 | 0.7363 | 0.8581 |
|
| 230 |
+
| No log | 3.9778 | 358 | 0.6416 | 0.6347 | 0.6416 | 0.8010 |
|
| 231 |
+
| No log | 4.0 | 360 | 0.6252 | 0.6589 | 0.6252 | 0.7907 |
|
| 232 |
+
| No log | 4.0222 | 362 | 0.6336 | 0.6589 | 0.6336 | 0.7960 |
|
| 233 |
+
| No log | 4.0444 | 364 | 0.6398 | 0.6447 | 0.6398 | 0.7999 |
|
| 234 |
+
| No log | 4.0667 | 366 | 0.6549 | 0.6447 | 0.6549 | 0.8093 |
|
| 235 |
+
| No log | 4.0889 | 368 | 0.6615 | 0.6355 | 0.6615 | 0.8134 |
|
| 236 |
+
| No log | 4.1111 | 370 | 0.6598 | 0.6408 | 0.6598 | 0.8123 |
|
| 237 |
+
| No log | 4.1333 | 372 | 0.6493 | 0.6408 | 0.6493 | 0.8058 |
|
| 238 |
+
| No log | 4.1556 | 374 | 0.6406 | 0.6286 | 0.6406 | 0.8004 |
|
| 239 |
+
| No log | 4.1778 | 376 | 0.6409 | 0.4957 | 0.6409 | 0.8005 |
|
| 240 |
+
| No log | 4.2 | 378 | 0.6418 | 0.5819 | 0.6418 | 0.8011 |
|
| 241 |
+
| No log | 4.2222 | 380 | 0.6366 | 0.6167 | 0.6366 | 0.7979 |
|
| 242 |
+
| No log | 4.2444 | 382 | 0.6295 | 0.6399 | 0.6295 | 0.7934 |
|
| 243 |
+
| No log | 4.2667 | 384 | 0.6355 | 0.6484 | 0.6355 | 0.7972 |
|
| 244 |
+
| No log | 4.2889 | 386 | 0.6471 | 0.5772 | 0.6471 | 0.8044 |
|
| 245 |
+
| No log | 4.3111 | 388 | 0.6143 | 0.6060 | 0.6143 | 0.7838 |
|
| 246 |
+
| No log | 4.3333 | 390 | 0.6166 | 0.6129 | 0.6166 | 0.7852 |
|
| 247 |
+
| No log | 4.3556 | 392 | 0.6069 | 0.5726 | 0.6069 | 0.7791 |
|
| 248 |
+
| No log | 4.3778 | 394 | 0.6111 | 0.6650 | 0.6111 | 0.7817 |
|
| 249 |
+
| No log | 4.4 | 396 | 0.6445 | 0.6909 | 0.6445 | 0.8028 |
|
| 250 |
+
| No log | 4.4222 | 398 | 0.6656 | 0.6805 | 0.6656 | 0.8159 |
|
| 251 |
+
| No log | 4.4444 | 400 | 0.6511 | 0.6846 | 0.6511 | 0.8069 |
|
| 252 |
+
| No log | 4.4667 | 402 | 0.6306 | 0.6690 | 0.6306 | 0.7941 |
|
| 253 |
+
| No log | 4.4889 | 404 | 0.6290 | 0.6097 | 0.6290 | 0.7931 |
|
| 254 |
+
| No log | 4.5111 | 406 | 0.6142 | 0.6409 | 0.6142 | 0.7837 |
|
| 255 |
+
| No log | 4.5333 | 408 | 0.5995 | 0.6830 | 0.5995 | 0.7742 |
|
| 256 |
+
| No log | 4.5556 | 410 | 0.5949 | 0.6923 | 0.5949 | 0.7713 |
|
| 257 |
+
| No log | 4.5778 | 412 | 0.6073 | 0.7054 | 0.6073 | 0.7793 |
|
| 258 |
+
| No log | 4.6 | 414 | 0.6467 | 0.6472 | 0.6467 | 0.8042 |
|
| 259 |
+
| No log | 4.6222 | 416 | 0.6606 | 0.6446 | 0.6606 | 0.8128 |
|
| 260 |
+
| No log | 4.6444 | 418 | 0.6677 | 0.6476 | 0.6677 | 0.8172 |
|
| 261 |
+
| No log | 4.6667 | 420 | 0.7456 | 0.5841 | 0.7456 | 0.8635 |
|
| 262 |
+
| No log | 4.6889 | 422 | 0.7070 | 0.5344 | 0.7070 | 0.8409 |
|
| 263 |
+
| No log | 4.7111 | 424 | 0.6359 | 0.5809 | 0.6359 | 0.7974 |
|
| 264 |
+
| No log | 4.7333 | 426 | 0.6830 | 0.5763 | 0.6830 | 0.8264 |
|
| 265 |
+
| No log | 4.7556 | 428 | 0.8293 | 0.5266 | 0.8293 | 0.9107 |
|
| 266 |
+
| No log | 4.7778 | 430 | 0.8823 | 0.5604 | 0.8823 | 0.9393 |
|
| 267 |
+
| No log | 4.8 | 432 | 0.8024 | 0.6025 | 0.8024 | 0.8958 |
|
| 268 |
+
| No log | 4.8222 | 434 | 0.6827 | 0.6602 | 0.6827 | 0.8263 |
|
| 269 |
+
| No log | 4.8444 | 436 | 0.6588 | 0.5275 | 0.6588 | 0.8116 |
|
| 270 |
+
| No log | 4.8667 | 438 | 0.6567 | 0.5068 | 0.6567 | 0.8104 |
|
| 271 |
+
| No log | 4.8889 | 440 | 0.6353 | 0.5845 | 0.6353 | 0.7970 |
|
| 272 |
+
| No log | 4.9111 | 442 | 0.6492 | 0.6311 | 0.6492 | 0.8057 |
|
| 273 |
+
| No log | 4.9333 | 444 | 0.6618 | 0.6325 | 0.6618 | 0.8135 |
|
| 274 |
+
| No log | 4.9556 | 446 | 0.6406 | 0.5886 | 0.6406 | 0.8004 |
|
| 275 |
+
| No log | 4.9778 | 448 | 0.6651 | 0.5343 | 0.6651 | 0.8155 |
|
| 276 |
+
| No log | 5.0 | 450 | 0.6623 | 0.5228 | 0.6623 | 0.8138 |
|
| 277 |
+
| No log | 5.0222 | 452 | 0.6231 | 0.5856 | 0.6231 | 0.7894 |
|
| 278 |
+
| No log | 5.0444 | 454 | 0.6333 | 0.6120 | 0.6333 | 0.7958 |
|
| 279 |
+
| No log | 5.0667 | 456 | 0.6521 | 0.6733 | 0.6521 | 0.8075 |
|
| 280 |
+
| No log | 5.0889 | 458 | 0.6825 | 0.6326 | 0.6825 | 0.8261 |
|
| 281 |
+
| No log | 5.1111 | 460 | 0.7244 | 0.5987 | 0.7244 | 0.8511 |
|
| 282 |
+
| No log | 5.1333 | 462 | 0.7223 | 0.5730 | 0.7223 | 0.8499 |
|
| 283 |
+
| No log | 5.1556 | 464 | 0.6741 | 0.5707 | 0.6741 | 0.8210 |
|
| 284 |
+
| No log | 5.1778 | 466 | 0.6585 | 0.6051 | 0.6585 | 0.8115 |
|
| 285 |
+
| No log | 5.2 | 468 | 0.7177 | 0.6685 | 0.7177 | 0.8472 |
|
| 286 |
+
| No log | 5.2222 | 470 | 0.7885 | 0.5877 | 0.7885 | 0.8880 |
|
| 287 |
+
| No log | 5.2444 | 472 | 0.7754 | 0.6145 | 0.7754 | 0.8806 |
|
| 288 |
+
| No log | 5.2667 | 474 | 0.7041 | 0.5972 | 0.7041 | 0.8391 |
|
| 289 |
+
| No log | 5.2889 | 476 | 0.6521 | 0.5884 | 0.6521 | 0.8075 |
|
| 290 |
+
| No log | 5.3111 | 478 | 0.6536 | 0.5300 | 0.6536 | 0.8084 |
|
| 291 |
+
| No log | 5.3333 | 480 | 0.6679 | 0.5326 | 0.6679 | 0.8172 |
|
| 292 |
+
| No log | 5.3556 | 482 | 0.6477 | 0.6047 | 0.6477 | 0.8048 |
|
| 293 |
+
| No log | 5.3778 | 484 | 0.6176 | 0.6217 | 0.6176 | 0.7859 |
|
| 294 |
+
| No log | 5.4 | 486 | 0.6294 | 0.6732 | 0.6294 | 0.7933 |
|
| 295 |
+
| No log | 5.4222 | 488 | 0.6571 | 0.6684 | 0.6571 | 0.8106 |
|
| 296 |
+
| No log | 5.4444 | 490 | 0.6322 | 0.6449 | 0.6322 | 0.7951 |
|
| 297 |
+
| No log | 5.4667 | 492 | 0.6281 | 0.6486 | 0.6281 | 0.7925 |
|
| 298 |
+
| No log | 5.4889 | 494 | 0.6217 | 0.6266 | 0.6217 | 0.7885 |
|
| 299 |
+
| No log | 5.5111 | 496 | 0.6279 | 0.5759 | 0.6279 | 0.7924 |
|
| 300 |
+
| No log | 5.5333 | 498 | 0.6287 | 0.5759 | 0.6287 | 0.7929 |
|
| 301 |
+
| 0.2826 | 5.5556 | 500 | 0.6282 | 0.6498 | 0.6282 | 0.7926 |
|
| 302 |
+
| 0.2826 | 5.5778 | 502 | 0.6217 | 0.6575 | 0.6217 | 0.7884 |
|
| 303 |
+
| 0.2826 | 5.6 | 504 | 0.6158 | 0.6398 | 0.6158 | 0.7847 |
|
| 304 |
+
| 0.2826 | 5.6222 | 506 | 0.6317 | 0.5950 | 0.6317 | 0.7948 |
|
| 305 |
+
| 0.2826 | 5.6444 | 508 | 0.7153 | 0.5889 | 0.7153 | 0.8457 |
|
| 306 |
+
| 0.2826 | 5.6667 | 510 | 0.7640 | 0.5821 | 0.7640 | 0.8741 |
|
| 307 |
+
| 0.2826 | 5.6889 | 512 | 0.6955 | 0.5541 | 0.6955 | 0.8339 |
|
| 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 sha256:441e195b43f8073ba30b4db87aed7ed1e305713ed0cb939724d133b82718b0b2
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8205135920094138ff7bc7132c4e45bd442185271cc7e0410a5c2dcdece55dc9
|
| 3 |
+
size 5304
|