Training in progress, step 500
Browse files- README.md +319 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k14_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_k14_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: 0.5024
|
| 19 |
+
- Qwk: 0.4837
|
| 20 |
+
- Mse: 0.5024
|
| 21 |
+
- Rmse: 0.7088
|
| 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 | 0.0286 | 2 | 2.5764 | -0.0924 | 2.5764 | 1.6051 |
|
| 53 |
+
| No log | 0.0571 | 4 | 1.0613 | 0.2097 | 1.0613 | 1.0302 |
|
| 54 |
+
| No log | 0.0857 | 6 | 0.6830 | 0.1372 | 0.6830 | 0.8265 |
|
| 55 |
+
| No log | 0.1143 | 8 | 0.6625 | 0.0846 | 0.6625 | 0.8139 |
|
| 56 |
+
| No log | 0.1429 | 10 | 0.6745 | 0.3782 | 0.6745 | 0.8213 |
|
| 57 |
+
| No log | 0.1714 | 12 | 0.7336 | 0.3008 | 0.7336 | 0.8565 |
|
| 58 |
+
| No log | 0.2 | 14 | 0.6543 | 0.3976 | 0.6543 | 0.8089 |
|
| 59 |
+
| No log | 0.2286 | 16 | 0.6221 | 0.4388 | 0.6221 | 0.7887 |
|
| 60 |
+
| No log | 0.2571 | 18 | 1.0317 | 0.2260 | 1.0317 | 1.0157 |
|
| 61 |
+
| No log | 0.2857 | 20 | 0.8947 | 0.4429 | 0.8947 | 0.9459 |
|
| 62 |
+
| No log | 0.3143 | 22 | 0.4931 | 0.4589 | 0.4931 | 0.7022 |
|
| 63 |
+
| No log | 0.3429 | 24 | 0.4410 | 0.5970 | 0.4410 | 0.6641 |
|
| 64 |
+
| No log | 0.3714 | 26 | 0.4519 | 0.6395 | 0.4519 | 0.6722 |
|
| 65 |
+
| No log | 0.4 | 28 | 0.5188 | 0.4832 | 0.5188 | 0.7203 |
|
| 66 |
+
| No log | 0.4286 | 30 | 0.7835 | 0.4413 | 0.7835 | 0.8851 |
|
| 67 |
+
| No log | 0.4571 | 32 | 0.8191 | 0.4222 | 0.8191 | 0.9050 |
|
| 68 |
+
| No log | 0.4857 | 34 | 0.5893 | 0.4569 | 0.5893 | 0.7677 |
|
| 69 |
+
| No log | 0.5143 | 36 | 0.6116 | 0.5770 | 0.6116 | 0.7821 |
|
| 70 |
+
| No log | 0.5429 | 38 | 0.7634 | 0.4438 | 0.7634 | 0.8737 |
|
| 71 |
+
| No log | 0.5714 | 40 | 0.7169 | 0.4175 | 0.7169 | 0.8467 |
|
| 72 |
+
| No log | 0.6 | 42 | 0.5431 | 0.5597 | 0.5431 | 0.7370 |
|
| 73 |
+
| No log | 0.6286 | 44 | 0.5202 | 0.5085 | 0.5202 | 0.7213 |
|
| 74 |
+
| No log | 0.6571 | 46 | 0.5575 | 0.5153 | 0.5575 | 0.7467 |
|
| 75 |
+
| No log | 0.6857 | 48 | 0.4649 | 0.6010 | 0.4649 | 0.6818 |
|
| 76 |
+
| No log | 0.7143 | 50 | 0.6390 | 0.4979 | 0.6390 | 0.7994 |
|
| 77 |
+
| No log | 0.7429 | 52 | 0.7952 | 0.5481 | 0.7952 | 0.8917 |
|
| 78 |
+
| No log | 0.7714 | 54 | 0.5706 | 0.5591 | 0.5706 | 0.7554 |
|
| 79 |
+
| No log | 0.8 | 56 | 0.4645 | 0.6027 | 0.4645 | 0.6815 |
|
| 80 |
+
| No log | 0.8286 | 58 | 0.5620 | 0.4575 | 0.5620 | 0.7496 |
|
| 81 |
+
| No log | 0.8571 | 60 | 0.5145 | 0.5300 | 0.5145 | 0.7173 |
|
| 82 |
+
| No log | 0.8857 | 62 | 0.4513 | 0.5731 | 0.4513 | 0.6718 |
|
| 83 |
+
| No log | 0.9143 | 64 | 0.4454 | 0.5714 | 0.4454 | 0.6674 |
|
| 84 |
+
| No log | 0.9429 | 66 | 0.5002 | 0.6437 | 0.5002 | 0.7073 |
|
| 85 |
+
| No log | 0.9714 | 68 | 0.5853 | 0.6075 | 0.5853 | 0.7651 |
|
| 86 |
+
| No log | 1.0 | 70 | 0.4683 | 0.6649 | 0.4683 | 0.6843 |
|
| 87 |
+
| No log | 1.0286 | 72 | 0.7428 | 0.5420 | 0.7428 | 0.8618 |
|
| 88 |
+
| No log | 1.0571 | 74 | 1.0819 | 0.3492 | 1.0819 | 1.0401 |
|
| 89 |
+
| No log | 1.0857 | 76 | 1.0221 | 0.4220 | 1.0221 | 1.0110 |
|
| 90 |
+
| No log | 1.1143 | 78 | 0.7472 | 0.4954 | 0.7472 | 0.8644 |
|
| 91 |
+
| No log | 1.1429 | 80 | 0.5167 | 0.6333 | 0.5167 | 0.7188 |
|
| 92 |
+
| No log | 1.1714 | 82 | 0.4366 | 0.6489 | 0.4366 | 0.6607 |
|
| 93 |
+
| No log | 1.2 | 84 | 0.4563 | 0.6434 | 0.4563 | 0.6755 |
|
| 94 |
+
| No log | 1.2286 | 86 | 0.4430 | 0.6423 | 0.4430 | 0.6656 |
|
| 95 |
+
| No log | 1.2571 | 88 | 0.4282 | 0.6661 | 0.4282 | 0.6544 |
|
| 96 |
+
| No log | 1.2857 | 90 | 0.4255 | 0.6229 | 0.4255 | 0.6523 |
|
| 97 |
+
| No log | 1.3143 | 92 | 0.4176 | 0.6724 | 0.4176 | 0.6462 |
|
| 98 |
+
| No log | 1.3429 | 94 | 0.4219 | 0.6724 | 0.4219 | 0.6495 |
|
| 99 |
+
| No log | 1.3714 | 96 | 0.4234 | 0.6716 | 0.4234 | 0.6507 |
|
| 100 |
+
| No log | 1.4 | 98 | 0.4689 | 0.5947 | 0.4689 | 0.6848 |
|
| 101 |
+
| No log | 1.4286 | 100 | 0.4571 | 0.5923 | 0.4571 | 0.6761 |
|
| 102 |
+
| No log | 1.4571 | 102 | 0.4354 | 0.6845 | 0.4354 | 0.6598 |
|
| 103 |
+
| No log | 1.4857 | 104 | 0.4515 | 0.6852 | 0.4515 | 0.6719 |
|
| 104 |
+
| No log | 1.5143 | 106 | 0.4706 | 0.6793 | 0.4706 | 0.6860 |
|
| 105 |
+
| No log | 1.5429 | 108 | 0.5563 | 0.6169 | 0.5563 | 0.7459 |
|
| 106 |
+
| No log | 1.5714 | 110 | 0.5209 | 0.6132 | 0.5209 | 0.7218 |
|
| 107 |
+
| No log | 1.6 | 112 | 0.4500 | 0.6526 | 0.4500 | 0.6708 |
|
| 108 |
+
| No log | 1.6286 | 114 | 0.5045 | 0.5852 | 0.5045 | 0.7102 |
|
| 109 |
+
| No log | 1.6571 | 116 | 0.4808 | 0.6080 | 0.4808 | 0.6934 |
|
| 110 |
+
| No log | 1.6857 | 118 | 0.4895 | 0.6017 | 0.4895 | 0.6997 |
|
| 111 |
+
| No log | 1.7143 | 120 | 0.5789 | 0.5450 | 0.5789 | 0.7608 |
|
| 112 |
+
| No log | 1.7429 | 122 | 0.4893 | 0.6620 | 0.4893 | 0.6995 |
|
| 113 |
+
| No log | 1.7714 | 124 | 0.4936 | 0.5409 | 0.4936 | 0.7025 |
|
| 114 |
+
| No log | 1.8 | 126 | 0.5978 | 0.5542 | 0.5978 | 0.7732 |
|
| 115 |
+
| No log | 1.8286 | 128 | 0.5020 | 0.5625 | 0.5020 | 0.7085 |
|
| 116 |
+
| No log | 1.8571 | 130 | 0.4364 | 0.7022 | 0.4364 | 0.6606 |
|
| 117 |
+
| No log | 1.8857 | 132 | 0.4364 | 0.7032 | 0.4364 | 0.6606 |
|
| 118 |
+
| No log | 1.9143 | 134 | 0.4802 | 0.5256 | 0.4802 | 0.6929 |
|
| 119 |
+
| No log | 1.9429 | 136 | 0.5788 | 0.5614 | 0.5788 | 0.7608 |
|
| 120 |
+
| No log | 1.9714 | 138 | 0.5643 | 0.5916 | 0.5643 | 0.7512 |
|
| 121 |
+
| No log | 2.0 | 140 | 0.4648 | 0.6286 | 0.4648 | 0.6818 |
|
| 122 |
+
| No log | 2.0286 | 142 | 0.4688 | 0.6286 | 0.4688 | 0.6847 |
|
| 123 |
+
| No log | 2.0571 | 144 | 0.5333 | 0.5396 | 0.5333 | 0.7303 |
|
| 124 |
+
| No log | 2.0857 | 146 | 0.5544 | 0.5639 | 0.5544 | 0.7446 |
|
| 125 |
+
| No log | 2.1143 | 148 | 0.5990 | 0.5326 | 0.5990 | 0.7739 |
|
| 126 |
+
| No log | 2.1429 | 150 | 0.4978 | 0.5324 | 0.4978 | 0.7055 |
|
| 127 |
+
| No log | 2.1714 | 152 | 0.4720 | 0.6970 | 0.4720 | 0.6870 |
|
| 128 |
+
| No log | 2.2 | 154 | 0.4839 | 0.7062 | 0.4839 | 0.6956 |
|
| 129 |
+
| No log | 2.2286 | 156 | 0.4858 | 0.5723 | 0.4858 | 0.6970 |
|
| 130 |
+
| No log | 2.2571 | 158 | 0.6098 | 0.4893 | 0.6098 | 0.7809 |
|
| 131 |
+
| No log | 2.2857 | 160 | 0.5737 | 0.5040 | 0.5737 | 0.7574 |
|
| 132 |
+
| No log | 2.3143 | 162 | 0.5204 | 0.4997 | 0.5204 | 0.7214 |
|
| 133 |
+
| No log | 2.3429 | 164 | 0.4567 | 0.6111 | 0.4567 | 0.6758 |
|
| 134 |
+
| No log | 2.3714 | 166 | 0.4670 | 0.7256 | 0.4670 | 0.6834 |
|
| 135 |
+
| No log | 2.4 | 168 | 0.5506 | 0.5190 | 0.5506 | 0.7420 |
|
| 136 |
+
| No log | 2.4286 | 170 | 0.4933 | 0.6803 | 0.4933 | 0.7024 |
|
| 137 |
+
| No log | 2.4571 | 172 | 0.4800 | 0.5701 | 0.4800 | 0.6928 |
|
| 138 |
+
| No log | 2.4857 | 174 | 0.5855 | 0.5428 | 0.5855 | 0.7652 |
|
| 139 |
+
| No log | 2.5143 | 176 | 0.5552 | 0.5261 | 0.5552 | 0.7451 |
|
| 140 |
+
| No log | 2.5429 | 178 | 0.4671 | 0.5886 | 0.4671 | 0.6834 |
|
| 141 |
+
| No log | 2.5714 | 180 | 0.4655 | 0.6761 | 0.4655 | 0.6823 |
|
| 142 |
+
| No log | 2.6 | 182 | 0.5196 | 0.5706 | 0.5196 | 0.7209 |
|
| 143 |
+
| No log | 2.6286 | 184 | 0.4972 | 0.6156 | 0.4972 | 0.7052 |
|
| 144 |
+
| No log | 2.6571 | 186 | 0.4637 | 0.6553 | 0.4637 | 0.6810 |
|
| 145 |
+
| No log | 2.6857 | 188 | 0.5354 | 0.5433 | 0.5354 | 0.7317 |
|
| 146 |
+
| No log | 2.7143 | 190 | 0.6461 | 0.6051 | 0.6461 | 0.8038 |
|
| 147 |
+
| No log | 2.7429 | 192 | 0.6101 | 0.5871 | 0.6101 | 0.7811 |
|
| 148 |
+
| No log | 2.7714 | 194 | 0.4906 | 0.6198 | 0.4906 | 0.7004 |
|
| 149 |
+
| No log | 2.8 | 196 | 0.5069 | 0.6170 | 0.5069 | 0.7120 |
|
| 150 |
+
| No log | 2.8286 | 198 | 0.5320 | 0.5168 | 0.5320 | 0.7294 |
|
| 151 |
+
| No log | 2.8571 | 200 | 0.4880 | 0.5918 | 0.4880 | 0.6985 |
|
| 152 |
+
| No log | 2.8857 | 202 | 0.4710 | 0.6289 | 0.4710 | 0.6863 |
|
| 153 |
+
| No log | 2.9143 | 204 | 0.4852 | 0.6449 | 0.4852 | 0.6965 |
|
| 154 |
+
| No log | 2.9429 | 206 | 0.4939 | 0.5872 | 0.4939 | 0.7028 |
|
| 155 |
+
| No log | 2.9714 | 208 | 0.5151 | 0.5947 | 0.5151 | 0.7177 |
|
| 156 |
+
| No log | 3.0 | 210 | 0.4860 | 0.6096 | 0.4860 | 0.6971 |
|
| 157 |
+
| No log | 3.0286 | 212 | 0.4683 | 0.5208 | 0.4683 | 0.6843 |
|
| 158 |
+
| No log | 3.0571 | 214 | 0.4653 | 0.5765 | 0.4653 | 0.6821 |
|
| 159 |
+
| No log | 3.0857 | 216 | 0.5067 | 0.5642 | 0.5067 | 0.7118 |
|
| 160 |
+
| No log | 3.1143 | 218 | 0.5543 | 0.5378 | 0.5543 | 0.7445 |
|
| 161 |
+
| No log | 3.1429 | 220 | 0.5177 | 0.5738 | 0.5177 | 0.7195 |
|
| 162 |
+
| No log | 3.1714 | 222 | 0.4579 | 0.6650 | 0.4579 | 0.6767 |
|
| 163 |
+
| No log | 3.2 | 224 | 0.5391 | 0.5056 | 0.5391 | 0.7342 |
|
| 164 |
+
| No log | 3.2286 | 226 | 0.5587 | 0.4933 | 0.5587 | 0.7475 |
|
| 165 |
+
| No log | 3.2571 | 228 | 0.4791 | 0.5937 | 0.4791 | 0.6922 |
|
| 166 |
+
| No log | 3.2857 | 230 | 0.4642 | 0.6849 | 0.4642 | 0.6813 |
|
| 167 |
+
| No log | 3.3143 | 232 | 0.4722 | 0.6065 | 0.4722 | 0.6872 |
|
| 168 |
+
| No log | 3.3429 | 234 | 0.5391 | 0.4951 | 0.5391 | 0.7342 |
|
| 169 |
+
| No log | 3.3714 | 236 | 0.5436 | 0.5173 | 0.5436 | 0.7373 |
|
| 170 |
+
| No log | 3.4 | 238 | 0.5129 | 0.6096 | 0.5129 | 0.7162 |
|
| 171 |
+
| No log | 3.4286 | 240 | 0.5213 | 0.6127 | 0.5213 | 0.7220 |
|
| 172 |
+
| No log | 3.4571 | 242 | 0.5077 | 0.6388 | 0.5077 | 0.7125 |
|
| 173 |
+
| No log | 3.4857 | 244 | 0.4967 | 0.6313 | 0.4967 | 0.7048 |
|
| 174 |
+
| No log | 3.5143 | 246 | 0.4829 | 0.6305 | 0.4829 | 0.6949 |
|
| 175 |
+
| No log | 3.5429 | 248 | 0.4644 | 0.6542 | 0.4644 | 0.6815 |
|
| 176 |
+
| No log | 3.5714 | 250 | 0.4786 | 0.5831 | 0.4786 | 0.6918 |
|
| 177 |
+
| No log | 3.6 | 252 | 0.4866 | 0.6058 | 0.4866 | 0.6975 |
|
| 178 |
+
| No log | 3.6286 | 254 | 0.4857 | 0.6481 | 0.4857 | 0.6969 |
|
| 179 |
+
| No log | 3.6571 | 256 | 0.5175 | 0.6127 | 0.5175 | 0.7194 |
|
| 180 |
+
| No log | 3.6857 | 258 | 0.4949 | 0.5797 | 0.4949 | 0.7035 |
|
| 181 |
+
| No log | 3.7143 | 260 | 0.4901 | 0.5218 | 0.4901 | 0.7001 |
|
| 182 |
+
| No log | 3.7429 | 262 | 0.5351 | 0.5499 | 0.5351 | 0.7315 |
|
| 183 |
+
| No log | 3.7714 | 264 | 0.5133 | 0.5756 | 0.5133 | 0.7164 |
|
| 184 |
+
| No log | 3.8 | 266 | 0.5098 | 0.5231 | 0.5098 | 0.7140 |
|
| 185 |
+
| No log | 3.8286 | 268 | 0.5263 | 0.5781 | 0.5263 | 0.7254 |
|
| 186 |
+
| No log | 3.8571 | 270 | 0.5103 | 0.4991 | 0.5103 | 0.7144 |
|
| 187 |
+
| No log | 3.8857 | 272 | 0.5186 | 0.5150 | 0.5186 | 0.7202 |
|
| 188 |
+
| No log | 3.9143 | 274 | 0.5192 | 0.5089 | 0.5192 | 0.7205 |
|
| 189 |
+
| No log | 3.9429 | 276 | 0.5270 | 0.5390 | 0.5270 | 0.7260 |
|
| 190 |
+
| No log | 3.9714 | 278 | 0.6483 | 0.4909 | 0.6483 | 0.8052 |
|
| 191 |
+
| No log | 4.0 | 280 | 0.6729 | 0.5122 | 0.6729 | 0.8203 |
|
| 192 |
+
| No log | 4.0286 | 282 | 0.5751 | 0.5569 | 0.5751 | 0.7583 |
|
| 193 |
+
| No log | 4.0571 | 284 | 0.5180 | 0.4463 | 0.5180 | 0.7197 |
|
| 194 |
+
| No log | 4.0857 | 286 | 0.5776 | 0.5104 | 0.5776 | 0.7600 |
|
| 195 |
+
| No log | 4.1143 | 288 | 0.6001 | 0.5237 | 0.6001 | 0.7747 |
|
| 196 |
+
| No log | 4.1429 | 290 | 0.5714 | 0.5437 | 0.5714 | 0.7559 |
|
| 197 |
+
| No log | 4.1714 | 292 | 0.5336 | 0.5095 | 0.5336 | 0.7305 |
|
| 198 |
+
| No log | 4.2 | 294 | 0.5122 | 0.6096 | 0.5122 | 0.7156 |
|
| 199 |
+
| No log | 4.2286 | 296 | 0.4947 | 0.6096 | 0.4947 | 0.7033 |
|
| 200 |
+
| No log | 4.2571 | 298 | 0.5234 | 0.5577 | 0.5234 | 0.7235 |
|
| 201 |
+
| No log | 4.2857 | 300 | 0.5200 | 0.5485 | 0.5200 | 0.7211 |
|
| 202 |
+
| No log | 4.3143 | 302 | 0.4740 | 0.6214 | 0.4740 | 0.6885 |
|
| 203 |
+
| No log | 4.3429 | 304 | 0.4882 | 0.6609 | 0.4882 | 0.6987 |
|
| 204 |
+
| No log | 4.3714 | 306 | 0.5344 | 0.5090 | 0.5344 | 0.7310 |
|
| 205 |
+
| No log | 4.4 | 308 | 0.5489 | 0.5421 | 0.5489 | 0.7409 |
|
| 206 |
+
| No log | 4.4286 | 310 | 0.5122 | 0.6084 | 0.5122 | 0.7157 |
|
| 207 |
+
| No log | 4.4571 | 312 | 0.5061 | 0.6427 | 0.5061 | 0.7114 |
|
| 208 |
+
| No log | 4.4857 | 314 | 0.5022 | 0.6904 | 0.5022 | 0.7086 |
|
| 209 |
+
| No log | 4.5143 | 316 | 0.5036 | 0.6815 | 0.5036 | 0.7096 |
|
| 210 |
+
| No log | 4.5429 | 318 | 0.4935 | 0.6438 | 0.4935 | 0.7025 |
|
| 211 |
+
| No log | 4.5714 | 320 | 0.4713 | 0.6542 | 0.4713 | 0.6865 |
|
| 212 |
+
| No log | 4.6 | 322 | 0.4669 | 0.5768 | 0.4669 | 0.6833 |
|
| 213 |
+
| No log | 4.6286 | 324 | 0.4639 | 0.5768 | 0.4639 | 0.6811 |
|
| 214 |
+
| No log | 4.6571 | 326 | 0.4614 | 0.6330 | 0.4614 | 0.6793 |
|
| 215 |
+
| No log | 4.6857 | 328 | 0.4733 | 0.6491 | 0.4733 | 0.6879 |
|
| 216 |
+
| No log | 4.7143 | 330 | 0.4851 | 0.6772 | 0.4851 | 0.6965 |
|
| 217 |
+
| No log | 4.7429 | 332 | 0.4915 | 0.6772 | 0.4915 | 0.7011 |
|
| 218 |
+
| No log | 4.7714 | 334 | 0.4926 | 0.6763 | 0.4926 | 0.7018 |
|
| 219 |
+
| No log | 4.8 | 336 | 0.4819 | 0.6087 | 0.4819 | 0.6942 |
|
| 220 |
+
| No log | 4.8286 | 338 | 0.4734 | 0.6255 | 0.4734 | 0.6881 |
|
| 221 |
+
| No log | 4.8571 | 340 | 0.4825 | 0.5648 | 0.4825 | 0.6947 |
|
| 222 |
+
| No log | 4.8857 | 342 | 0.5021 | 0.5550 | 0.5021 | 0.7086 |
|
| 223 |
+
| No log | 4.9143 | 344 | 0.5024 | 0.5648 | 0.5024 | 0.7088 |
|
| 224 |
+
| No log | 4.9429 | 346 | 0.4916 | 0.5095 | 0.4916 | 0.7011 |
|
| 225 |
+
| No log | 4.9714 | 348 | 0.4983 | 0.5815 | 0.4983 | 0.7059 |
|
| 226 |
+
| No log | 5.0 | 350 | 0.5029 | 0.5584 | 0.5029 | 0.7092 |
|
| 227 |
+
| No log | 5.0286 | 352 | 0.5266 | 0.5528 | 0.5266 | 0.7257 |
|
| 228 |
+
| No log | 5.0571 | 354 | 0.5589 | 0.6022 | 0.5589 | 0.7476 |
|
| 229 |
+
| No log | 5.0857 | 356 | 0.5317 | 0.5966 | 0.5317 | 0.7292 |
|
| 230 |
+
| No log | 5.1143 | 358 | 0.5112 | 0.6007 | 0.5112 | 0.7149 |
|
| 231 |
+
| No log | 5.1429 | 360 | 0.5007 | 0.5707 | 0.5007 | 0.7076 |
|
| 232 |
+
| No log | 5.1714 | 362 | 0.5105 | 0.4985 | 0.5105 | 0.7145 |
|
| 233 |
+
| No log | 5.2 | 364 | 0.5990 | 0.4093 | 0.5990 | 0.7739 |
|
| 234 |
+
| No log | 5.2286 | 366 | 0.6036 | 0.4144 | 0.6036 | 0.7769 |
|
| 235 |
+
| No log | 5.2571 | 368 | 0.5293 | 0.5053 | 0.5293 | 0.7275 |
|
| 236 |
+
| No log | 5.2857 | 370 | 0.5043 | 0.5022 | 0.5043 | 0.7102 |
|
| 237 |
+
| No log | 5.3143 | 372 | 0.5141 | 0.5071 | 0.5141 | 0.7170 |
|
| 238 |
+
| No log | 5.3429 | 374 | 0.5497 | 0.5093 | 0.5497 | 0.7414 |
|
| 239 |
+
| No log | 5.3714 | 376 | 0.6263 | 0.4967 | 0.6263 | 0.7914 |
|
| 240 |
+
| No log | 5.4 | 378 | 0.5747 | 0.5076 | 0.5747 | 0.7581 |
|
| 241 |
+
| No log | 5.4286 | 380 | 0.5133 | 0.5053 | 0.5133 | 0.7165 |
|
| 242 |
+
| No log | 5.4571 | 382 | 0.5013 | 0.5289 | 0.5013 | 0.7080 |
|
| 243 |
+
| No log | 5.4857 | 384 | 0.4920 | 0.5379 | 0.4920 | 0.7014 |
|
| 244 |
+
| No log | 5.5143 | 386 | 0.4914 | 0.5344 | 0.4914 | 0.7010 |
|
| 245 |
+
| No log | 5.5429 | 388 | 0.4889 | 0.5861 | 0.4889 | 0.6992 |
|
| 246 |
+
| No log | 5.5714 | 390 | 0.4895 | 0.5781 | 0.4895 | 0.6996 |
|
| 247 |
+
| No log | 5.6 | 392 | 0.4845 | 0.5956 | 0.4845 | 0.6960 |
|
| 248 |
+
| No log | 5.6286 | 394 | 0.5240 | 0.5872 | 0.5240 | 0.7239 |
|
| 249 |
+
| No log | 5.6571 | 396 | 0.5875 | 0.5700 | 0.5875 | 0.7665 |
|
| 250 |
+
| No log | 5.6857 | 398 | 0.6059 | 0.5508 | 0.6059 | 0.7784 |
|
| 251 |
+
| No log | 5.7143 | 400 | 0.5300 | 0.4984 | 0.5300 | 0.7280 |
|
| 252 |
+
| No log | 5.7429 | 402 | 0.4975 | 0.5344 | 0.4975 | 0.7053 |
|
| 253 |
+
| No log | 5.7714 | 404 | 0.4981 | 0.5117 | 0.4981 | 0.7058 |
|
| 254 |
+
| No log | 5.8 | 406 | 0.5195 | 0.5438 | 0.5195 | 0.7208 |
|
| 255 |
+
| No log | 5.8286 | 408 | 0.5070 | 0.5656 | 0.5070 | 0.7120 |
|
| 256 |
+
| No log | 5.8571 | 410 | 0.5843 | 0.4862 | 0.5843 | 0.7644 |
|
| 257 |
+
| No log | 5.8857 | 412 | 0.6310 | 0.4536 | 0.6310 | 0.7944 |
|
| 258 |
+
| No log | 5.9143 | 414 | 0.5780 | 0.5015 | 0.5780 | 0.7603 |
|
| 259 |
+
| No log | 5.9429 | 416 | 0.5227 | 0.4768 | 0.5227 | 0.7229 |
|
| 260 |
+
| No log | 5.9714 | 418 | 0.5650 | 0.5422 | 0.5650 | 0.7517 |
|
| 261 |
+
| No log | 6.0 | 420 | 0.6063 | 0.5368 | 0.6063 | 0.7786 |
|
| 262 |
+
| No log | 6.0286 | 422 | 0.5726 | 0.5422 | 0.5726 | 0.7567 |
|
| 263 |
+
| No log | 6.0571 | 424 | 0.5626 | 0.4402 | 0.5626 | 0.7501 |
|
| 264 |
+
| No log | 6.0857 | 426 | 0.5761 | 0.5109 | 0.5761 | 0.7590 |
|
| 265 |
+
| No log | 6.1143 | 428 | 0.5867 | 0.5032 | 0.5867 | 0.7660 |
|
| 266 |
+
| No log | 6.1429 | 430 | 0.5476 | 0.5404 | 0.5476 | 0.7400 |
|
| 267 |
+
| No log | 6.1714 | 432 | 0.5353 | 0.4240 | 0.5353 | 0.7316 |
|
| 268 |
+
| No log | 6.2 | 434 | 0.5434 | 0.5028 | 0.5434 | 0.7371 |
|
| 269 |
+
| No log | 6.2286 | 436 | 0.5287 | 0.4505 | 0.5287 | 0.7271 |
|
| 270 |
+
| No log | 6.2571 | 438 | 0.5229 | 0.5404 | 0.5229 | 0.7231 |
|
| 271 |
+
| No log | 6.2857 | 440 | 0.5676 | 0.4945 | 0.5676 | 0.7534 |
|
| 272 |
+
| No log | 6.3143 | 442 | 0.5932 | 0.4451 | 0.5932 | 0.7702 |
|
| 273 |
+
| No log | 6.3429 | 444 | 0.5592 | 0.4945 | 0.5592 | 0.7478 |
|
| 274 |
+
| No log | 6.3714 | 446 | 0.5250 | 0.4837 | 0.5250 | 0.7246 |
|
| 275 |
+
| No log | 6.4 | 448 | 0.5185 | 0.4788 | 0.5185 | 0.7200 |
|
| 276 |
+
| No log | 6.4286 | 450 | 0.5251 | 0.5042 | 0.5251 | 0.7246 |
|
| 277 |
+
| No log | 6.4571 | 452 | 0.5446 | 0.4171 | 0.5446 | 0.7379 |
|
| 278 |
+
| No log | 6.4857 | 454 | 0.5968 | 0.4568 | 0.5968 | 0.7725 |
|
| 279 |
+
| No log | 6.5143 | 456 | 0.6205 | 0.4701 | 0.6205 | 0.7877 |
|
| 280 |
+
| No log | 6.5429 | 458 | 0.5721 | 0.5015 | 0.5721 | 0.7564 |
|
| 281 |
+
| No log | 6.5714 | 460 | 0.5284 | 0.3890 | 0.5284 | 0.7269 |
|
| 282 |
+
| No log | 6.6 | 462 | 0.5247 | 0.4217 | 0.5247 | 0.7244 |
|
| 283 |
+
| No log | 6.6286 | 464 | 0.5373 | 0.5319 | 0.5373 | 0.7330 |
|
| 284 |
+
| No log | 6.6571 | 466 | 0.5342 | 0.5596 | 0.5342 | 0.7309 |
|
| 285 |
+
| No log | 6.6857 | 468 | 0.5452 | 0.4985 | 0.5452 | 0.7384 |
|
| 286 |
+
| No log | 6.7143 | 470 | 0.6078 | 0.4484 | 0.6078 | 0.7796 |
|
| 287 |
+
| No log | 6.7429 | 472 | 0.7134 | 0.4385 | 0.7134 | 0.8446 |
|
| 288 |
+
| No log | 6.7714 | 474 | 0.7136 | 0.4438 | 0.7136 | 0.8448 |
|
| 289 |
+
| No log | 6.8 | 476 | 0.6009 | 0.4239 | 0.6009 | 0.7752 |
|
| 290 |
+
| No log | 6.8286 | 478 | 0.5335 | 0.5034 | 0.5335 | 0.7304 |
|
| 291 |
+
| No log | 6.8571 | 480 | 0.5104 | 0.4788 | 0.5104 | 0.7144 |
|
| 292 |
+
| No log | 6.8857 | 482 | 0.5088 | 0.5446 | 0.5088 | 0.7133 |
|
| 293 |
+
| No log | 6.9143 | 484 | 0.5069 | 0.4788 | 0.5069 | 0.7119 |
|
| 294 |
+
| No log | 6.9429 | 486 | 0.5068 | 0.4788 | 0.5068 | 0.7119 |
|
| 295 |
+
| No log | 6.9714 | 488 | 0.5062 | 0.4788 | 0.5062 | 0.7115 |
|
| 296 |
+
| No log | 7.0 | 490 | 0.5056 | 0.4788 | 0.5056 | 0.7110 |
|
| 297 |
+
| No log | 7.0286 | 492 | 0.4979 | 0.5042 | 0.4979 | 0.7056 |
|
| 298 |
+
| No log | 7.0571 | 494 | 0.4912 | 0.5672 | 0.4912 | 0.7009 |
|
| 299 |
+
| No log | 7.0857 | 496 | 0.4954 | 0.6197 | 0.4954 | 0.7039 |
|
| 300 |
+
| No log | 7.1143 | 498 | 0.4890 | 0.5042 | 0.4890 | 0.6993 |
|
| 301 |
+
| 0.2811 | 7.1429 | 500 | 0.5006 | 0.5344 | 0.5006 | 0.7075 |
|
| 302 |
+
| 0.2811 | 7.1714 | 502 | 0.5340 | 0.5034 | 0.5340 | 0.7308 |
|
| 303 |
+
| 0.2811 | 7.2 | 504 | 0.5622 | 0.5166 | 0.5622 | 0.7498 |
|
| 304 |
+
| 0.2811 | 7.2286 | 506 | 0.6062 | 0.5204 | 0.6062 | 0.7786 |
|
| 305 |
+
| 0.2811 | 7.2571 | 508 | 0.5673 | 0.5591 | 0.5673 | 0.7532 |
|
| 306 |
+
| 0.2811 | 7.2857 | 510 | 0.5100 | 0.5584 | 0.5100 | 0.7142 |
|
| 307 |
+
| 0.2811 | 7.3143 | 512 | 0.4936 | 0.5042 | 0.4936 | 0.7025 |
|
| 308 |
+
| 0.2811 | 7.3429 | 514 | 0.4911 | 0.5042 | 0.4911 | 0.7008 |
|
| 309 |
+
| 0.2811 | 7.3714 | 516 | 0.4959 | 0.5344 | 0.4959 | 0.7042 |
|
| 310 |
+
| 0.2811 | 7.4 | 518 | 0.4938 | 0.5095 | 0.4938 | 0.7027 |
|
| 311 |
+
| 0.2811 | 7.4286 | 520 | 0.5024 | 0.4837 | 0.5024 | 0.7088 |
|
| 312 |
+
|
| 313 |
+
|
| 314 |
+
### Framework versions
|
| 315 |
+
|
| 316 |
+
- Transformers 4.44.2
|
| 317 |
+
- Pytorch 2.4.0+cu118
|
| 318 |
+
- Datasets 2.21.0
|
| 319 |
+
- 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 sha256:88a5a4b49618350b9e7df247ece5b95d0f55aa5067bec7d8ae84a5d65159a20d
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:022cab4db83471903ecc76593ad111a2427f178738d735c61e310453d1bafeab
|
| 3 |
+
size 5304
|