Training in progress, step 500
Browse files- README.md +337 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k3_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_k3_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: 0.5725
|
| 19 |
+
- Qwk: 0.5607
|
| 20 |
+
- Mse: 0.5725
|
| 21 |
+
- Rmse: 0.7567
|
| 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 | 0.1333 | 2 | 4.2058 | -0.0177 | 4.2058 | 2.0508 |
|
| 53 |
+
| No log | 0.2667 | 4 | 3.2834 | -0.0036 | 3.2834 | 1.8120 |
|
| 54 |
+
| No log | 0.4 | 6 | 1.3955 | 0.0760 | 1.3955 | 1.1813 |
|
| 55 |
+
| No log | 0.5333 | 8 | 1.1705 | 0.0967 | 1.1705 | 1.0819 |
|
| 56 |
+
| No log | 0.6667 | 10 | 1.0616 | 0.3541 | 1.0616 | 1.0304 |
|
| 57 |
+
| No log | 0.8 | 12 | 1.0069 | 0.2643 | 1.0069 | 1.0034 |
|
| 58 |
+
| No log | 0.9333 | 14 | 0.9937 | 0.2740 | 0.9937 | 0.9969 |
|
| 59 |
+
| No log | 1.0667 | 16 | 0.9431 | 0.2944 | 0.9431 | 0.9711 |
|
| 60 |
+
| No log | 1.2 | 18 | 0.9770 | 0.3935 | 0.9770 | 0.9884 |
|
| 61 |
+
| No log | 1.3333 | 20 | 1.1137 | 0.1498 | 1.1137 | 1.0553 |
|
| 62 |
+
| No log | 1.4667 | 22 | 1.0486 | 0.2969 | 1.0486 | 1.0240 |
|
| 63 |
+
| No log | 1.6 | 24 | 0.9977 | 0.3003 | 0.9977 | 0.9988 |
|
| 64 |
+
| No log | 1.7333 | 26 | 1.0085 | 0.2787 | 1.0085 | 1.0042 |
|
| 65 |
+
| No log | 1.8667 | 28 | 1.0653 | 0.1962 | 1.0653 | 1.0321 |
|
| 66 |
+
| No log | 2.0 | 30 | 1.0453 | 0.2175 | 1.0453 | 1.0224 |
|
| 67 |
+
| No log | 2.1333 | 32 | 0.9974 | 0.2175 | 0.9974 | 0.9987 |
|
| 68 |
+
| No log | 2.2667 | 34 | 0.8223 | 0.3883 | 0.8223 | 0.9068 |
|
| 69 |
+
| No log | 2.4 | 36 | 0.7608 | 0.4733 | 0.7608 | 0.8722 |
|
| 70 |
+
| No log | 2.5333 | 38 | 0.7471 | 0.5348 | 0.7471 | 0.8643 |
|
| 71 |
+
| No log | 2.6667 | 40 | 0.7775 | 0.4444 | 0.7775 | 0.8818 |
|
| 72 |
+
| No log | 2.8 | 42 | 0.9123 | 0.4462 | 0.9123 | 0.9551 |
|
| 73 |
+
| No log | 2.9333 | 44 | 0.9203 | 0.4094 | 0.9203 | 0.9593 |
|
| 74 |
+
| No log | 3.0667 | 46 | 0.8834 | 0.3208 | 0.8834 | 0.9399 |
|
| 75 |
+
| No log | 3.2 | 48 | 0.7497 | 0.5343 | 0.7497 | 0.8658 |
|
| 76 |
+
| No log | 3.3333 | 50 | 0.6601 | 0.5704 | 0.6601 | 0.8125 |
|
| 77 |
+
| No log | 3.4667 | 52 | 0.7183 | 0.5141 | 0.7183 | 0.8475 |
|
| 78 |
+
| No log | 3.6 | 54 | 0.6538 | 0.5225 | 0.6538 | 0.8086 |
|
| 79 |
+
| No log | 3.7333 | 56 | 0.6184 | 0.6073 | 0.6184 | 0.7864 |
|
| 80 |
+
| No log | 3.8667 | 58 | 0.6722 | 0.6043 | 0.6722 | 0.8199 |
|
| 81 |
+
| No log | 4.0 | 60 | 0.6707 | 0.5771 | 0.6707 | 0.8190 |
|
| 82 |
+
| No log | 4.1333 | 62 | 0.6482 | 0.6239 | 0.6482 | 0.8051 |
|
| 83 |
+
| No log | 4.2667 | 64 | 0.6322 | 0.5969 | 0.6322 | 0.7951 |
|
| 84 |
+
| No log | 4.4 | 66 | 0.6335 | 0.6073 | 0.6335 | 0.7959 |
|
| 85 |
+
| No log | 4.5333 | 68 | 0.6238 | 0.5690 | 0.6238 | 0.7898 |
|
| 86 |
+
| No log | 4.6667 | 70 | 0.6038 | 0.6498 | 0.6038 | 0.7771 |
|
| 87 |
+
| No log | 4.8 | 72 | 0.6148 | 0.6237 | 0.6148 | 0.7841 |
|
| 88 |
+
| No log | 4.9333 | 74 | 0.5941 | 0.6206 | 0.5941 | 0.7708 |
|
| 89 |
+
| No log | 5.0667 | 76 | 0.5846 | 0.6319 | 0.5846 | 0.7646 |
|
| 90 |
+
| No log | 5.2 | 78 | 0.5746 | 0.6484 | 0.5746 | 0.7580 |
|
| 91 |
+
| No log | 5.3333 | 80 | 0.5699 | 0.6484 | 0.5699 | 0.7549 |
|
| 92 |
+
| No log | 5.4667 | 82 | 0.6716 | 0.6766 | 0.6716 | 0.8195 |
|
| 93 |
+
| No log | 5.6 | 84 | 0.7061 | 0.6487 | 0.7061 | 0.8403 |
|
| 94 |
+
| No log | 5.7333 | 86 | 0.6205 | 0.6647 | 0.6205 | 0.7877 |
|
| 95 |
+
| No log | 5.8667 | 88 | 0.5941 | 0.6288 | 0.5941 | 0.7708 |
|
| 96 |
+
| No log | 6.0 | 90 | 0.6086 | 0.6619 | 0.6086 | 0.7801 |
|
| 97 |
+
| No log | 6.1333 | 92 | 0.6030 | 0.6439 | 0.6030 | 0.7765 |
|
| 98 |
+
| No log | 6.2667 | 94 | 0.6141 | 0.6664 | 0.6141 | 0.7836 |
|
| 99 |
+
| No log | 6.4 | 96 | 0.6500 | 0.6519 | 0.6500 | 0.8062 |
|
| 100 |
+
| No log | 6.5333 | 98 | 0.5991 | 0.6439 | 0.5991 | 0.7740 |
|
| 101 |
+
| No log | 6.6667 | 100 | 0.6770 | 0.6669 | 0.6770 | 0.8228 |
|
| 102 |
+
| No log | 6.8 | 102 | 0.6588 | 0.6548 | 0.6588 | 0.8117 |
|
| 103 |
+
| No log | 6.9333 | 104 | 0.5573 | 0.6545 | 0.5573 | 0.7465 |
|
| 104 |
+
| No log | 7.0667 | 106 | 0.7229 | 0.6128 | 0.7229 | 0.8502 |
|
| 105 |
+
| No log | 7.2 | 108 | 0.7203 | 0.6218 | 0.7203 | 0.8487 |
|
| 106 |
+
| No log | 7.3333 | 110 | 0.5605 | 0.6940 | 0.5605 | 0.7487 |
|
| 107 |
+
| No log | 7.4667 | 112 | 0.5271 | 0.6217 | 0.5271 | 0.7260 |
|
| 108 |
+
| No log | 7.6 | 114 | 0.5240 | 0.6916 | 0.5240 | 0.7238 |
|
| 109 |
+
| No log | 7.7333 | 116 | 0.5355 | 0.6424 | 0.5355 | 0.7317 |
|
| 110 |
+
| No log | 7.8667 | 118 | 0.5782 | 0.6500 | 0.5782 | 0.7604 |
|
| 111 |
+
| No log | 8.0 | 120 | 0.5890 | 0.6748 | 0.5890 | 0.7675 |
|
| 112 |
+
| No log | 8.1333 | 122 | 0.5422 | 0.6642 | 0.5422 | 0.7363 |
|
| 113 |
+
| No log | 8.2667 | 124 | 0.5571 | 0.6426 | 0.5571 | 0.7464 |
|
| 114 |
+
| No log | 8.4 | 126 | 0.5667 | 0.6606 | 0.5667 | 0.7528 |
|
| 115 |
+
| No log | 8.5333 | 128 | 0.5348 | 0.6642 | 0.5348 | 0.7313 |
|
| 116 |
+
| No log | 8.6667 | 130 | 0.6792 | 0.6304 | 0.6792 | 0.8241 |
|
| 117 |
+
| No log | 8.8 | 132 | 0.7280 | 0.6160 | 0.7280 | 0.8532 |
|
| 118 |
+
| No log | 8.9333 | 134 | 0.6795 | 0.4642 | 0.6795 | 0.8243 |
|
| 119 |
+
| No log | 9.0667 | 136 | 0.7695 | 0.5614 | 0.7695 | 0.8772 |
|
| 120 |
+
| No log | 9.2 | 138 | 0.6862 | 0.5829 | 0.6862 | 0.8284 |
|
| 121 |
+
| No log | 9.3333 | 140 | 0.5596 | 0.6465 | 0.5596 | 0.7481 |
|
| 122 |
+
| No log | 9.4667 | 142 | 0.5339 | 0.6614 | 0.5339 | 0.7307 |
|
| 123 |
+
| No log | 9.6 | 144 | 0.5344 | 0.6846 | 0.5344 | 0.7310 |
|
| 124 |
+
| No log | 9.7333 | 146 | 0.5646 | 0.6639 | 0.5646 | 0.7514 |
|
| 125 |
+
| No log | 9.8667 | 148 | 0.6631 | 0.6141 | 0.6631 | 0.8143 |
|
| 126 |
+
| No log | 10.0 | 150 | 0.6507 | 0.6141 | 0.6507 | 0.8067 |
|
| 127 |
+
| No log | 10.1333 | 152 | 0.5561 | 0.6371 | 0.5561 | 0.7457 |
|
| 128 |
+
| No log | 10.2667 | 154 | 0.5649 | 0.6473 | 0.5649 | 0.7516 |
|
| 129 |
+
| No log | 10.4 | 156 | 0.6344 | 0.6493 | 0.6344 | 0.7965 |
|
| 130 |
+
| No log | 10.5333 | 158 | 0.6055 | 0.6782 | 0.6055 | 0.7782 |
|
| 131 |
+
| No log | 10.6667 | 160 | 0.5454 | 0.6536 | 0.5454 | 0.7385 |
|
| 132 |
+
| No log | 10.8 | 162 | 0.5457 | 0.6822 | 0.5457 | 0.7387 |
|
| 133 |
+
| No log | 10.9333 | 164 | 0.6129 | 0.5593 | 0.6129 | 0.7829 |
|
| 134 |
+
| No log | 11.0667 | 166 | 0.6598 | 0.5527 | 0.6598 | 0.8123 |
|
| 135 |
+
| No log | 11.2 | 168 | 0.6002 | 0.5708 | 0.6002 | 0.7747 |
|
| 136 |
+
| No log | 11.3333 | 170 | 0.5377 | 0.6319 | 0.5377 | 0.7333 |
|
| 137 |
+
| No log | 11.4667 | 172 | 0.5588 | 0.6923 | 0.5588 | 0.7475 |
|
| 138 |
+
| No log | 11.6 | 174 | 0.5359 | 0.6923 | 0.5359 | 0.7320 |
|
| 139 |
+
| No log | 11.7333 | 176 | 0.5339 | 0.7106 | 0.5339 | 0.7307 |
|
| 140 |
+
| No log | 11.8667 | 178 | 0.5738 | 0.6395 | 0.5738 | 0.7575 |
|
| 141 |
+
| No log | 12.0 | 180 | 0.5694 | 0.6218 | 0.5694 | 0.7546 |
|
| 142 |
+
| No log | 12.1333 | 182 | 0.5524 | 0.7059 | 0.5524 | 0.7432 |
|
| 143 |
+
| No log | 12.2667 | 184 | 0.5483 | 0.6400 | 0.5483 | 0.7405 |
|
| 144 |
+
| No log | 12.4 | 186 | 0.5261 | 0.7026 | 0.5261 | 0.7254 |
|
| 145 |
+
| No log | 12.5333 | 188 | 0.5329 | 0.6328 | 0.5329 | 0.7300 |
|
| 146 |
+
| No log | 12.6667 | 190 | 0.5238 | 0.6724 | 0.5238 | 0.7237 |
|
| 147 |
+
| No log | 12.8 | 192 | 0.5210 | 0.6909 | 0.5210 | 0.7218 |
|
| 148 |
+
| No log | 12.9333 | 194 | 0.5209 | 0.6766 | 0.5209 | 0.7217 |
|
| 149 |
+
| No log | 13.0667 | 196 | 0.5590 | 0.6275 | 0.5590 | 0.7476 |
|
| 150 |
+
| No log | 13.2 | 198 | 0.6286 | 0.6597 | 0.6286 | 0.7929 |
|
| 151 |
+
| No log | 13.3333 | 200 | 0.5886 | 0.6275 | 0.5886 | 0.7672 |
|
| 152 |
+
| No log | 13.4667 | 202 | 0.5413 | 0.6032 | 0.5413 | 0.7357 |
|
| 153 |
+
| No log | 13.6 | 204 | 0.5629 | 0.6990 | 0.5629 | 0.7503 |
|
| 154 |
+
| No log | 13.7333 | 206 | 0.5507 | 0.6215 | 0.5507 | 0.7421 |
|
| 155 |
+
| No log | 13.8667 | 208 | 0.6228 | 0.6698 | 0.6228 | 0.7892 |
|
| 156 |
+
| No log | 14.0 | 210 | 0.6987 | 0.6712 | 0.6987 | 0.8359 |
|
| 157 |
+
| No log | 14.1333 | 212 | 0.6210 | 0.6035 | 0.6210 | 0.7881 |
|
| 158 |
+
| No log | 14.2667 | 214 | 0.5849 | 0.6157 | 0.5849 | 0.7648 |
|
| 159 |
+
| No log | 14.4 | 216 | 0.5940 | 0.6147 | 0.5940 | 0.7707 |
|
| 160 |
+
| No log | 14.5333 | 218 | 0.6007 | 0.6147 | 0.6007 | 0.7750 |
|
| 161 |
+
| No log | 14.6667 | 220 | 0.5792 | 0.6473 | 0.5792 | 0.7611 |
|
| 162 |
+
| No log | 14.8 | 222 | 0.5667 | 0.6536 | 0.5667 | 0.7528 |
|
| 163 |
+
| No log | 14.9333 | 224 | 0.5852 | 0.6087 | 0.5852 | 0.7650 |
|
| 164 |
+
| No log | 15.0667 | 226 | 0.5978 | 0.5961 | 0.5978 | 0.7731 |
|
| 165 |
+
| No log | 15.2 | 228 | 0.5716 | 0.6018 | 0.5716 | 0.7561 |
|
| 166 |
+
| No log | 15.3333 | 230 | 0.5898 | 0.6167 | 0.5898 | 0.7680 |
|
| 167 |
+
| No log | 15.4667 | 232 | 0.6125 | 0.5833 | 0.6125 | 0.7826 |
|
| 168 |
+
| No log | 15.6 | 234 | 0.6425 | 0.5938 | 0.6425 | 0.8016 |
|
| 169 |
+
| No log | 15.7333 | 236 | 0.5954 | 0.5921 | 0.5954 | 0.7716 |
|
| 170 |
+
| No log | 15.8667 | 238 | 0.5957 | 0.5933 | 0.5957 | 0.7718 |
|
| 171 |
+
| No log | 16.0 | 240 | 0.6549 | 0.6259 | 0.6549 | 0.8092 |
|
| 172 |
+
| No log | 16.1333 | 242 | 0.5984 | 0.6334 | 0.5984 | 0.7736 |
|
| 173 |
+
| No log | 16.2667 | 244 | 0.5636 | 0.6078 | 0.5636 | 0.7507 |
|
| 174 |
+
| No log | 16.4 | 246 | 0.5829 | 0.5948 | 0.5829 | 0.7635 |
|
| 175 |
+
| No log | 16.5333 | 248 | 0.6378 | 0.5799 | 0.6378 | 0.7986 |
|
| 176 |
+
| No log | 16.6667 | 250 | 0.6001 | 0.5510 | 0.6001 | 0.7747 |
|
| 177 |
+
| No log | 16.8 | 252 | 0.5855 | 0.6320 | 0.5855 | 0.7652 |
|
| 178 |
+
| No log | 16.9333 | 254 | 0.5883 | 0.6667 | 0.5883 | 0.7670 |
|
| 179 |
+
| No log | 17.0667 | 256 | 0.5653 | 0.6672 | 0.5653 | 0.7519 |
|
| 180 |
+
| No log | 17.2 | 258 | 0.5983 | 0.6404 | 0.5983 | 0.7735 |
|
| 181 |
+
| No log | 17.3333 | 260 | 0.6478 | 0.5973 | 0.6478 | 0.8048 |
|
| 182 |
+
| No log | 17.4667 | 262 | 0.6520 | 0.5777 | 0.6520 | 0.8075 |
|
| 183 |
+
| No log | 17.6 | 264 | 0.5950 | 0.6025 | 0.5950 | 0.7714 |
|
| 184 |
+
| No log | 17.7333 | 266 | 0.5918 | 0.5948 | 0.5918 | 0.7693 |
|
| 185 |
+
| No log | 17.8667 | 268 | 0.5916 | 0.5645 | 0.5916 | 0.7692 |
|
| 186 |
+
| No log | 18.0 | 270 | 0.6474 | 0.5833 | 0.6474 | 0.8046 |
|
| 187 |
+
| No log | 18.1333 | 272 | 0.6947 | 0.5591 | 0.6947 | 0.8335 |
|
| 188 |
+
| No log | 18.2667 | 274 | 0.6459 | 0.5998 | 0.6459 | 0.8037 |
|
| 189 |
+
| No log | 18.4 | 276 | 0.5546 | 0.5959 | 0.5546 | 0.7447 |
|
| 190 |
+
| No log | 18.5333 | 278 | 0.5282 | 0.6748 | 0.5282 | 0.7268 |
|
| 191 |
+
| No log | 18.6667 | 280 | 0.5226 | 0.6642 | 0.5226 | 0.7229 |
|
| 192 |
+
| No log | 18.8 | 282 | 0.5690 | 0.6830 | 0.5690 | 0.7544 |
|
| 193 |
+
| No log | 18.9333 | 284 | 0.6135 | 0.6690 | 0.6135 | 0.7833 |
|
| 194 |
+
| No log | 19.0667 | 286 | 0.5948 | 0.6573 | 0.5948 | 0.7712 |
|
| 195 |
+
| No log | 19.2 | 288 | 0.5611 | 0.6237 | 0.5611 | 0.7491 |
|
| 196 |
+
| No log | 19.3333 | 290 | 0.5533 | 0.6745 | 0.5533 | 0.7439 |
|
| 197 |
+
| No log | 19.4667 | 292 | 0.5763 | 0.6102 | 0.5763 | 0.7591 |
|
| 198 |
+
| No log | 19.6 | 294 | 0.5925 | 0.5975 | 0.5925 | 0.7697 |
|
| 199 |
+
| No log | 19.7333 | 296 | 0.5602 | 0.6441 | 0.5602 | 0.7485 |
|
| 200 |
+
| No log | 19.8667 | 298 | 0.5425 | 0.6301 | 0.5425 | 0.7365 |
|
| 201 |
+
| No log | 20.0 | 300 | 0.5591 | 0.6147 | 0.5591 | 0.7478 |
|
| 202 |
+
| No log | 20.1333 | 302 | 0.5518 | 0.6647 | 0.5518 | 0.7428 |
|
| 203 |
+
| No log | 20.2667 | 304 | 0.5290 | 0.6347 | 0.5290 | 0.7273 |
|
| 204 |
+
| No log | 20.4 | 306 | 0.5504 | 0.6328 | 0.5504 | 0.7419 |
|
| 205 |
+
| No log | 20.5333 | 308 | 0.6119 | 0.6459 | 0.6119 | 0.7822 |
|
| 206 |
+
| No log | 20.6667 | 310 | 0.6111 | 0.6287 | 0.6111 | 0.7817 |
|
| 207 |
+
| No log | 20.8 | 312 | 0.5906 | 0.6109 | 0.5906 | 0.7685 |
|
| 208 |
+
| No log | 20.9333 | 314 | 0.5453 | 0.6641 | 0.5453 | 0.7385 |
|
| 209 |
+
| No log | 21.0667 | 316 | 0.5547 | 0.6437 | 0.5547 | 0.7448 |
|
| 210 |
+
| No log | 21.2 | 318 | 0.5567 | 0.6575 | 0.5567 | 0.7461 |
|
| 211 |
+
| No log | 21.3333 | 320 | 0.5876 | 0.5833 | 0.5876 | 0.7666 |
|
| 212 |
+
| No log | 21.4667 | 322 | 0.6894 | 0.6209 | 0.6894 | 0.8303 |
|
| 213 |
+
| No log | 21.6 | 324 | 0.7613 | 0.6078 | 0.7613 | 0.8725 |
|
| 214 |
+
| No log | 21.7333 | 326 | 0.7426 | 0.6377 | 0.7426 | 0.8617 |
|
| 215 |
+
| No log | 21.8667 | 328 | 0.6634 | 0.6141 | 0.6634 | 0.8145 |
|
| 216 |
+
| No log | 22.0 | 330 | 0.5796 | 0.6073 | 0.5796 | 0.7613 |
|
| 217 |
+
| No log | 22.1333 | 332 | 0.5845 | 0.6133 | 0.5845 | 0.7645 |
|
| 218 |
+
| No log | 22.2667 | 334 | 0.5865 | 0.6133 | 0.5865 | 0.7659 |
|
| 219 |
+
| No log | 22.4 | 336 | 0.5878 | 0.6102 | 0.5878 | 0.7667 |
|
| 220 |
+
| No log | 22.5333 | 338 | 0.6949 | 0.5666 | 0.6949 | 0.8336 |
|
| 221 |
+
| No log | 22.6667 | 340 | 0.8333 | 0.5966 | 0.8333 | 0.9129 |
|
| 222 |
+
| No log | 22.8 | 342 | 0.8298 | 0.5966 | 0.8298 | 0.9109 |
|
| 223 |
+
| No log | 22.9333 | 344 | 0.7184 | 0.6035 | 0.7184 | 0.8476 |
|
| 224 |
+
| No log | 23.0667 | 346 | 0.6143 | 0.6063 | 0.6143 | 0.7838 |
|
| 225 |
+
| No log | 23.2 | 348 | 0.5761 | 0.6430 | 0.5761 | 0.7590 |
|
| 226 |
+
| No log | 23.3333 | 350 | 0.5737 | 0.6430 | 0.5737 | 0.7574 |
|
| 227 |
+
| No log | 23.4667 | 352 | 0.5921 | 0.6446 | 0.5921 | 0.7695 |
|
| 228 |
+
| No log | 23.6 | 354 | 0.6558 | 0.5487 | 0.6558 | 0.8098 |
|
| 229 |
+
| No log | 23.7333 | 356 | 0.6905 | 0.5666 | 0.6905 | 0.8310 |
|
| 230 |
+
| No log | 23.8667 | 358 | 0.6410 | 0.5697 | 0.6410 | 0.8007 |
|
| 231 |
+
| No log | 24.0 | 360 | 0.5942 | 0.6035 | 0.5942 | 0.7708 |
|
| 232 |
+
| No log | 24.1333 | 362 | 0.5809 | 0.6177 | 0.5809 | 0.7622 |
|
| 233 |
+
| No log | 24.2667 | 364 | 0.5549 | 0.6593 | 0.5549 | 0.7449 |
|
| 234 |
+
| No log | 24.4 | 366 | 0.5544 | 0.6593 | 0.5544 | 0.7446 |
|
| 235 |
+
| No log | 24.5333 | 368 | 0.5661 | 0.6473 | 0.5661 | 0.7524 |
|
| 236 |
+
| No log | 24.6667 | 370 | 0.6078 | 0.5602 | 0.6078 | 0.7796 |
|
| 237 |
+
| No log | 24.8 | 372 | 0.6206 | 0.5487 | 0.6206 | 0.7878 |
|
| 238 |
+
| No log | 24.9333 | 374 | 0.6383 | 0.5487 | 0.6383 | 0.7989 |
|
| 239 |
+
| No log | 25.0667 | 376 | 0.6240 | 0.5487 | 0.6240 | 0.7899 |
|
| 240 |
+
| No log | 25.2 | 378 | 0.5837 | 0.5833 | 0.5837 | 0.7640 |
|
| 241 |
+
| No log | 25.3333 | 380 | 0.5767 | 0.6167 | 0.5767 | 0.7594 |
|
| 242 |
+
| No log | 25.4667 | 382 | 0.5548 | 0.6282 | 0.5548 | 0.7449 |
|
| 243 |
+
| No log | 25.6 | 384 | 0.5408 | 0.6396 | 0.5408 | 0.7354 |
|
| 244 |
+
| No log | 25.7333 | 386 | 0.5542 | 0.6282 | 0.5542 | 0.7444 |
|
| 245 |
+
| No log | 25.8667 | 388 | 0.5845 | 0.5988 | 0.5845 | 0.7645 |
|
| 246 |
+
| No log | 26.0 | 390 | 0.6206 | 0.5988 | 0.6206 | 0.7878 |
|
| 247 |
+
| No log | 26.1333 | 392 | 0.6231 | 0.5877 | 0.6231 | 0.7894 |
|
| 248 |
+
| No log | 26.2667 | 394 | 0.6055 | 0.5988 | 0.6055 | 0.7781 |
|
| 249 |
+
| No log | 26.4 | 396 | 0.5600 | 0.6063 | 0.5600 | 0.7483 |
|
| 250 |
+
| No log | 26.5333 | 398 | 0.5291 | 0.6712 | 0.5291 | 0.7274 |
|
| 251 |
+
| No log | 26.6667 | 400 | 0.5281 | 0.6509 | 0.5281 | 0.7267 |
|
| 252 |
+
| No log | 26.8 | 402 | 0.5235 | 0.6572 | 0.5235 | 0.7235 |
|
| 253 |
+
| No log | 26.9333 | 404 | 0.5392 | 0.6396 | 0.5392 | 0.7343 |
|
| 254 |
+
| No log | 27.0667 | 406 | 0.5803 | 0.6319 | 0.5803 | 0.7618 |
|
| 255 |
+
| No log | 27.2 | 408 | 0.6282 | 0.5877 | 0.6282 | 0.7926 |
|
| 256 |
+
| No log | 27.3333 | 410 | 0.6341 | 0.5602 | 0.6341 | 0.7963 |
|
| 257 |
+
| No log | 27.4667 | 412 | 0.6180 | 0.5602 | 0.6180 | 0.7861 |
|
| 258 |
+
| No log | 27.6 | 414 | 0.5901 | 0.5948 | 0.5901 | 0.7682 |
|
| 259 |
+
| No log | 27.7333 | 416 | 0.5687 | 0.6241 | 0.5687 | 0.7541 |
|
| 260 |
+
| No log | 27.8667 | 418 | 0.5599 | 0.6113 | 0.5599 | 0.7483 |
|
| 261 |
+
| No log | 28.0 | 420 | 0.5525 | 0.6227 | 0.5525 | 0.7433 |
|
| 262 |
+
| No log | 28.1333 | 422 | 0.5402 | 0.6732 | 0.5402 | 0.7350 |
|
| 263 |
+
| No log | 28.2667 | 424 | 0.5756 | 0.6493 | 0.5756 | 0.7587 |
|
| 264 |
+
| No log | 28.4 | 426 | 0.6073 | 0.6071 | 0.6073 | 0.7793 |
|
| 265 |
+
| No log | 28.5333 | 428 | 0.6348 | 0.6071 | 0.6348 | 0.7968 |
|
| 266 |
+
| No log | 28.6667 | 430 | 0.6452 | 0.5718 | 0.6452 | 0.8032 |
|
| 267 |
+
| No log | 28.8 | 432 | 0.6369 | 0.5718 | 0.6369 | 0.7981 |
|
| 268 |
+
| No log | 28.9333 | 434 | 0.6063 | 0.6053 | 0.6063 | 0.7786 |
|
| 269 |
+
| No log | 29.0667 | 436 | 0.5912 | 0.6167 | 0.5912 | 0.7689 |
|
| 270 |
+
| No log | 29.2 | 438 | 0.5724 | 0.6464 | 0.5724 | 0.7566 |
|
| 271 |
+
| No log | 29.3333 | 440 | 0.5666 | 0.6464 | 0.5666 | 0.7528 |
|
| 272 |
+
| No log | 29.4667 | 442 | 0.6067 | 0.6247 | 0.6067 | 0.7789 |
|
| 273 |
+
| No log | 29.6 | 444 | 0.6109 | 0.6061 | 0.6109 | 0.7816 |
|
| 274 |
+
| No log | 29.7333 | 446 | 0.5830 | 0.5799 | 0.5830 | 0.7636 |
|
| 275 |
+
| No log | 29.8667 | 448 | 0.5461 | 0.6113 | 0.5461 | 0.7390 |
|
| 276 |
+
| No log | 30.0 | 450 | 0.5525 | 0.6466 | 0.5525 | 0.7433 |
|
| 277 |
+
| No log | 30.1333 | 452 | 0.5546 | 0.6657 | 0.5546 | 0.7447 |
|
| 278 |
+
| No log | 30.2667 | 454 | 0.5579 | 0.6025 | 0.5579 | 0.7469 |
|
| 279 |
+
| No log | 30.4 | 456 | 0.5750 | 0.5912 | 0.5750 | 0.7583 |
|
| 280 |
+
| No log | 30.5333 | 458 | 0.5680 | 0.6352 | 0.5680 | 0.7537 |
|
| 281 |
+
| No log | 30.6667 | 460 | 0.5530 | 0.6748 | 0.5530 | 0.7436 |
|
| 282 |
+
| No log | 30.8 | 462 | 0.5546 | 0.6748 | 0.5546 | 0.7447 |
|
| 283 |
+
| No log | 30.9333 | 464 | 0.5425 | 0.6259 | 0.5425 | 0.7366 |
|
| 284 |
+
| No log | 31.0667 | 466 | 0.5467 | 0.6259 | 0.5467 | 0.7394 |
|
| 285 |
+
| No log | 31.2 | 468 | 0.5646 | 0.6575 | 0.5646 | 0.7514 |
|
| 286 |
+
| No log | 31.3333 | 470 | 0.5954 | 0.6127 | 0.5954 | 0.7716 |
|
| 287 |
+
| No log | 31.4667 | 472 | 0.5932 | 0.6240 | 0.5932 | 0.7702 |
|
| 288 |
+
| No log | 31.6 | 474 | 0.5794 | 0.6352 | 0.5794 | 0.7612 |
|
| 289 |
+
| No log | 31.7333 | 476 | 0.5599 | 0.6575 | 0.5599 | 0.7483 |
|
| 290 |
+
| No log | 31.8667 | 478 | 0.5447 | 0.6259 | 0.5447 | 0.7381 |
|
| 291 |
+
| No log | 32.0 | 480 | 0.5473 | 0.6259 | 0.5473 | 0.7398 |
|
| 292 |
+
| No log | 32.1333 | 482 | 0.5836 | 0.6529 | 0.5836 | 0.7639 |
|
| 293 |
+
| No log | 32.2667 | 484 | 0.6213 | 0.6278 | 0.6213 | 0.7882 |
|
| 294 |
+
| No log | 32.4 | 486 | 0.6192 | 0.6099 | 0.6192 | 0.7869 |
|
| 295 |
+
| No log | 32.5333 | 488 | 0.5764 | 0.6464 | 0.5764 | 0.7592 |
|
| 296 |
+
| No log | 32.6667 | 490 | 0.5489 | 0.6219 | 0.5489 | 0.7409 |
|
| 297 |
+
| No log | 32.8 | 492 | 0.5572 | 0.6286 | 0.5572 | 0.7465 |
|
| 298 |
+
| No log | 32.9333 | 494 | 0.5649 | 0.6241 | 0.5649 | 0.7516 |
|
| 299 |
+
| No log | 33.0667 | 496 | 0.5987 | 0.5948 | 0.5987 | 0.7737 |
|
| 300 |
+
| No log | 33.2 | 498 | 0.6847 | 0.5877 | 0.6847 | 0.8275 |
|
| 301 |
+
| 0.2491 | 33.3333 | 500 | 0.7345 | 0.5943 | 0.7345 | 0.8570 |
|
| 302 |
+
| 0.2491 | 33.4667 | 502 | 0.7043 | 0.5766 | 0.7043 | 0.8392 |
|
| 303 |
+
| 0.2491 | 33.6 | 504 | 0.6132 | 0.5912 | 0.6132 | 0.7830 |
|
| 304 |
+
| 0.2491 | 33.7333 | 506 | 0.5464 | 0.6479 | 0.5464 | 0.7392 |
|
| 305 |
+
| 0.2491 | 33.8667 | 508 | 0.5488 | 0.6556 | 0.5488 | 0.7408 |
|
| 306 |
+
| 0.2491 | 34.0 | 510 | 0.5586 | 0.6447 | 0.5586 | 0.7474 |
|
| 307 |
+
| 0.2491 | 34.1333 | 512 | 0.5467 | 0.6374 | 0.5467 | 0.7394 |
|
| 308 |
+
| 0.2491 | 34.2667 | 514 | 0.5415 | 0.6415 | 0.5415 | 0.7359 |
|
| 309 |
+
| 0.2491 | 34.4 | 516 | 0.5832 | 0.6035 | 0.5832 | 0.7637 |
|
| 310 |
+
| 0.2491 | 34.5333 | 518 | 0.6146 | 0.6310 | 0.6146 | 0.7839 |
|
| 311 |
+
| 0.2491 | 34.6667 | 520 | 0.6007 | 0.6147 | 0.6007 | 0.7751 |
|
| 312 |
+
| 0.2491 | 34.8 | 522 | 0.5829 | 0.5959 | 0.5829 | 0.7635 |
|
| 313 |
+
| 0.2491 | 34.9333 | 524 | 0.5739 | 0.5959 | 0.5739 | 0.7576 |
|
| 314 |
+
| 0.2491 | 35.0667 | 526 | 0.5632 | 0.6065 | 0.5632 | 0.7505 |
|
| 315 |
+
| 0.2491 | 35.2 | 528 | 0.5556 | 0.6035 | 0.5556 | 0.7454 |
|
| 316 |
+
| 0.2491 | 35.3333 | 530 | 0.5519 | 0.5969 | 0.5519 | 0.7429 |
|
| 317 |
+
| 0.2491 | 35.4667 | 532 | 0.5710 | 0.6352 | 0.5710 | 0.7556 |
|
| 318 |
+
| 0.2491 | 35.6 | 534 | 0.5738 | 0.6352 | 0.5738 | 0.7575 |
|
| 319 |
+
| 0.2491 | 35.7333 | 536 | 0.5707 | 0.6249 | 0.5707 | 0.7555 |
|
| 320 |
+
| 0.2491 | 35.8667 | 538 | 0.5637 | 0.6249 | 0.5637 | 0.7508 |
|
| 321 |
+
| 0.2491 | 36.0 | 540 | 0.5625 | 0.6249 | 0.5625 | 0.7500 |
|
| 322 |
+
| 0.2491 | 36.1333 | 542 | 0.5631 | 0.5986 | 0.5631 | 0.7504 |
|
| 323 |
+
| 0.2491 | 36.2667 | 544 | 0.5641 | 0.5986 | 0.5641 | 0.7511 |
|
| 324 |
+
| 0.2491 | 36.4 | 546 | 0.5790 | 0.6500 | 0.5790 | 0.7609 |
|
| 325 |
+
| 0.2491 | 36.5333 | 548 | 0.6171 | 0.5799 | 0.6171 | 0.7856 |
|
| 326 |
+
| 0.2491 | 36.6667 | 550 | 0.6388 | 0.5686 | 0.6388 | 0.7993 |
|
| 327 |
+
| 0.2491 | 36.8 | 552 | 0.6172 | 0.5877 | 0.6172 | 0.7856 |
|
| 328 |
+
| 0.2491 | 36.9333 | 554 | 0.6027 | 0.5877 | 0.6027 | 0.7763 |
|
| 329 |
+
| 0.2491 | 37.0667 | 556 | 0.5725 | 0.5607 | 0.5725 | 0.7567 |
|
| 330 |
+
|
| 331 |
+
|
| 332 |
+
### Framework versions
|
| 333 |
+
|
| 334 |
+
- Transformers 4.44.2
|
| 335 |
+
- Pytorch 2.4.0+cu118
|
| 336 |
+
- Datasets 2.21.0
|
| 337 |
+
- 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:fe723b2ce617a1a9c2a7e8645613cdaa96794c572018344130ef901f9232e26d
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db4c5c9bf75483e12af697b0a6c429c7efd70bb8f2302a1542ab2f04379428e4
|
| 3 |
+
size 5304
|