Training in progress, step 500
Browse files- README.md +326 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask6_grammar
|
| 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 |
+
# Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask6_grammar
|
| 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: 0.5716
|
| 19 |
+
- Qwk: 0.5757
|
| 20 |
+
- Mse: 0.5716
|
| 21 |
+
- Rmse: 0.7560
|
| 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 | 0.0194 | 2 | 4.6545 | -0.0214 | 4.6545 | 2.1574 |
|
| 53 |
+
| No log | 0.0388 | 4 | 2.7259 | 0.0440 | 2.7259 | 1.6510 |
|
| 54 |
+
| No log | 0.0583 | 6 | 1.4363 | 0.0351 | 1.4363 | 1.1984 |
|
| 55 |
+
| No log | 0.0777 | 8 | 0.8380 | 0.1736 | 0.8380 | 0.9154 |
|
| 56 |
+
| No log | 0.0971 | 10 | 0.7015 | 0.2479 | 0.7015 | 0.8375 |
|
| 57 |
+
| No log | 0.1165 | 12 | 0.7047 | 0.1433 | 0.7047 | 0.8395 |
|
| 58 |
+
| No log | 0.1359 | 14 | 0.7369 | 0.1669 | 0.7369 | 0.8584 |
|
| 59 |
+
| No log | 0.1553 | 16 | 0.7415 | 0.1648 | 0.7415 | 0.8611 |
|
| 60 |
+
| No log | 0.1748 | 18 | 0.8791 | 0.1936 | 0.8791 | 0.9376 |
|
| 61 |
+
| No log | 0.1942 | 20 | 1.5824 | 0.0677 | 1.5824 | 1.2579 |
|
| 62 |
+
| No log | 0.2136 | 22 | 1.4080 | 0.1148 | 1.4080 | 1.1866 |
|
| 63 |
+
| No log | 0.2330 | 24 | 0.8231 | 0.2773 | 0.8231 | 0.9073 |
|
| 64 |
+
| No log | 0.2524 | 26 | 0.5790 | 0.3206 | 0.5790 | 0.7609 |
|
| 65 |
+
| No log | 0.2718 | 28 | 0.6999 | 0.1758 | 0.6999 | 0.8366 |
|
| 66 |
+
| No log | 0.2913 | 30 | 0.6414 | 0.2109 | 0.6414 | 0.8009 |
|
| 67 |
+
| No log | 0.3107 | 32 | 0.5569 | 0.3844 | 0.5569 | 0.7462 |
|
| 68 |
+
| No log | 0.3301 | 34 | 0.5638 | 0.4470 | 0.5638 | 0.7509 |
|
| 69 |
+
| No log | 0.3495 | 36 | 0.5842 | 0.3854 | 0.5842 | 0.7644 |
|
| 70 |
+
| No log | 0.3689 | 38 | 0.5960 | 0.3821 | 0.5960 | 0.7720 |
|
| 71 |
+
| No log | 0.3883 | 40 | 0.5704 | 0.4008 | 0.5704 | 0.7553 |
|
| 72 |
+
| No log | 0.4078 | 42 | 0.5522 | 0.4577 | 0.5522 | 0.7431 |
|
| 73 |
+
| No log | 0.4272 | 44 | 0.5444 | 0.5145 | 0.5444 | 0.7378 |
|
| 74 |
+
| No log | 0.4466 | 46 | 0.5460 | 0.5089 | 0.5460 | 0.7389 |
|
| 75 |
+
| No log | 0.4660 | 48 | 0.5958 | 0.5061 | 0.5958 | 0.7719 |
|
| 76 |
+
| No log | 0.4854 | 50 | 0.6412 | 0.5038 | 0.6412 | 0.8007 |
|
| 77 |
+
| No log | 0.5049 | 52 | 0.7626 | 0.4769 | 0.7626 | 0.8733 |
|
| 78 |
+
| No log | 0.5243 | 54 | 0.6720 | 0.4852 | 0.6720 | 0.8197 |
|
| 79 |
+
| No log | 0.5437 | 56 | 0.6008 | 0.5456 | 0.6008 | 0.7751 |
|
| 80 |
+
| No log | 0.5631 | 58 | 0.5317 | 0.5351 | 0.5317 | 0.7292 |
|
| 81 |
+
| No log | 0.5825 | 60 | 0.5529 | 0.3992 | 0.5529 | 0.7435 |
|
| 82 |
+
| No log | 0.6019 | 62 | 0.6467 | 0.2379 | 0.6467 | 0.8042 |
|
| 83 |
+
| No log | 0.6214 | 64 | 0.6519 | 0.2038 | 0.6519 | 0.8074 |
|
| 84 |
+
| No log | 0.6408 | 66 | 0.5984 | 0.2281 | 0.5984 | 0.7736 |
|
| 85 |
+
| No log | 0.6602 | 68 | 0.5865 | 0.2393 | 0.5865 | 0.7658 |
|
| 86 |
+
| No log | 0.6796 | 70 | 0.5819 | 0.2638 | 0.5819 | 0.7628 |
|
| 87 |
+
| No log | 0.6990 | 72 | 0.6064 | 0.2852 | 0.6064 | 0.7787 |
|
| 88 |
+
| No log | 0.7184 | 74 | 0.6024 | 0.3006 | 0.6024 | 0.7761 |
|
| 89 |
+
| No log | 0.7379 | 76 | 0.5880 | 0.3303 | 0.5880 | 0.7668 |
|
| 90 |
+
| No log | 0.7573 | 78 | 0.5543 | 0.4014 | 0.5543 | 0.7445 |
|
| 91 |
+
| No log | 0.7767 | 80 | 0.6039 | 0.4303 | 0.6039 | 0.7771 |
|
| 92 |
+
| No log | 0.7961 | 82 | 0.6884 | 0.3854 | 0.6884 | 0.8297 |
|
| 93 |
+
| No log | 0.8155 | 84 | 0.6038 | 0.4916 | 0.6038 | 0.7770 |
|
| 94 |
+
| No log | 0.8350 | 86 | 0.5193 | 0.4737 | 0.5193 | 0.7206 |
|
| 95 |
+
| No log | 0.8544 | 88 | 0.5262 | 0.4757 | 0.5262 | 0.7254 |
|
| 96 |
+
| No log | 0.8738 | 90 | 0.5654 | 0.4787 | 0.5654 | 0.7519 |
|
| 97 |
+
| No log | 0.8932 | 92 | 0.5377 | 0.5137 | 0.5377 | 0.7333 |
|
| 98 |
+
| No log | 0.9126 | 94 | 0.4853 | 0.5394 | 0.4853 | 0.6966 |
|
| 99 |
+
| No log | 0.9320 | 96 | 0.4972 | 0.5742 | 0.4972 | 0.7051 |
|
| 100 |
+
| No log | 0.9515 | 98 | 0.5283 | 0.5720 | 0.5283 | 0.7269 |
|
| 101 |
+
| No log | 0.9709 | 100 | 0.5336 | 0.5732 | 0.5336 | 0.7305 |
|
| 102 |
+
| No log | 0.9903 | 102 | 0.5841 | 0.5644 | 0.5841 | 0.7643 |
|
| 103 |
+
| No log | 1.0097 | 104 | 0.6572 | 0.5391 | 0.6572 | 0.8107 |
|
| 104 |
+
| No log | 1.0291 | 106 | 0.7438 | 0.3423 | 0.7438 | 0.8625 |
|
| 105 |
+
| No log | 1.0485 | 108 | 0.8559 | 0.2858 | 0.8559 | 0.9252 |
|
| 106 |
+
| No log | 1.0680 | 110 | 0.7397 | 0.3083 | 0.7397 | 0.8600 |
|
| 107 |
+
| No log | 1.0874 | 112 | 0.5669 | 0.4512 | 0.5669 | 0.7529 |
|
| 108 |
+
| No log | 1.1068 | 114 | 0.5004 | 0.5715 | 0.5004 | 0.7074 |
|
| 109 |
+
| No log | 1.1262 | 116 | 0.4792 | 0.5518 | 0.4792 | 0.6922 |
|
| 110 |
+
| No log | 1.1456 | 118 | 0.5171 | 0.5388 | 0.5171 | 0.7191 |
|
| 111 |
+
| No log | 1.1650 | 120 | 0.5677 | 0.4987 | 0.5677 | 0.7534 |
|
| 112 |
+
| No log | 1.1845 | 122 | 0.5123 | 0.4961 | 0.5123 | 0.7157 |
|
| 113 |
+
| No log | 1.2039 | 124 | 0.6051 | 0.4994 | 0.6051 | 0.7779 |
|
| 114 |
+
| No log | 1.2233 | 126 | 0.5715 | 0.5299 | 0.5715 | 0.7560 |
|
| 115 |
+
| No log | 1.2427 | 128 | 0.5504 | 0.5049 | 0.5504 | 0.7419 |
|
| 116 |
+
| No log | 1.2621 | 130 | 0.4478 | 0.5278 | 0.4478 | 0.6692 |
|
| 117 |
+
| No log | 1.2816 | 132 | 0.4424 | 0.5410 | 0.4424 | 0.6651 |
|
| 118 |
+
| No log | 1.3010 | 134 | 0.5270 | 0.5637 | 0.5270 | 0.7260 |
|
| 119 |
+
| No log | 1.3204 | 136 | 0.5390 | 0.5421 | 0.5390 | 0.7342 |
|
| 120 |
+
| No log | 1.3398 | 138 | 0.4542 | 0.5339 | 0.4542 | 0.6739 |
|
| 121 |
+
| No log | 1.3592 | 140 | 0.4411 | 0.5432 | 0.4411 | 0.6642 |
|
| 122 |
+
| No log | 1.3786 | 142 | 0.4980 | 0.5417 | 0.4980 | 0.7057 |
|
| 123 |
+
| No log | 1.3981 | 144 | 0.6240 | 0.5235 | 0.6240 | 0.7900 |
|
| 124 |
+
| No log | 1.4175 | 146 | 0.6735 | 0.5291 | 0.6735 | 0.8207 |
|
| 125 |
+
| No log | 1.4369 | 148 | 0.5989 | 0.5301 | 0.5989 | 0.7739 |
|
| 126 |
+
| No log | 1.4563 | 150 | 0.5410 | 0.5244 | 0.5410 | 0.7355 |
|
| 127 |
+
| No log | 1.4757 | 152 | 0.6051 | 0.5085 | 0.6051 | 0.7779 |
|
| 128 |
+
| No log | 1.4951 | 154 | 0.6147 | 0.5084 | 0.6147 | 0.7840 |
|
| 129 |
+
| No log | 1.5146 | 156 | 0.6051 | 0.4768 | 0.6051 | 0.7779 |
|
| 130 |
+
| No log | 1.5340 | 158 | 0.6878 | 0.4858 | 0.6878 | 0.8293 |
|
| 131 |
+
| No log | 1.5534 | 160 | 0.8004 | 0.4865 | 0.8004 | 0.8946 |
|
| 132 |
+
| No log | 1.5728 | 162 | 0.7777 | 0.5131 | 0.7777 | 0.8819 |
|
| 133 |
+
| No log | 1.5922 | 164 | 0.6453 | 0.5721 | 0.6453 | 0.8033 |
|
| 134 |
+
| No log | 1.6117 | 166 | 0.6097 | 0.5718 | 0.6097 | 0.7809 |
|
| 135 |
+
| No log | 1.6311 | 168 | 0.5600 | 0.5813 | 0.5600 | 0.7484 |
|
| 136 |
+
| No log | 1.6505 | 170 | 0.5061 | 0.5766 | 0.5061 | 0.7114 |
|
| 137 |
+
| No log | 1.6699 | 172 | 0.4845 | 0.5491 | 0.4845 | 0.6960 |
|
| 138 |
+
| No log | 1.6893 | 174 | 0.4818 | 0.5497 | 0.4818 | 0.6942 |
|
| 139 |
+
| No log | 1.7087 | 176 | 0.4678 | 0.5319 | 0.4678 | 0.6840 |
|
| 140 |
+
| No log | 1.7282 | 178 | 0.4889 | 0.5356 | 0.4889 | 0.6992 |
|
| 141 |
+
| No log | 1.7476 | 180 | 0.5018 | 0.5429 | 0.5018 | 0.7083 |
|
| 142 |
+
| No log | 1.7670 | 182 | 0.5020 | 0.5682 | 0.5020 | 0.7085 |
|
| 143 |
+
| No log | 1.7864 | 184 | 0.4740 | 0.5979 | 0.4740 | 0.6885 |
|
| 144 |
+
| No log | 1.8058 | 186 | 0.5502 | 0.5223 | 0.5502 | 0.7417 |
|
| 145 |
+
| No log | 1.8252 | 188 | 0.5452 | 0.5580 | 0.5452 | 0.7384 |
|
| 146 |
+
| No log | 1.8447 | 190 | 0.5029 | 0.5953 | 0.5029 | 0.7092 |
|
| 147 |
+
| No log | 1.8641 | 192 | 0.4626 | 0.5878 | 0.4626 | 0.6801 |
|
| 148 |
+
| No log | 1.8835 | 194 | 0.4846 | 0.5286 | 0.4846 | 0.6961 |
|
| 149 |
+
| No log | 1.9029 | 196 | 0.5039 | 0.4473 | 0.5039 | 0.7098 |
|
| 150 |
+
| No log | 1.9223 | 198 | 0.5397 | 0.5014 | 0.5397 | 0.7347 |
|
| 151 |
+
| No log | 1.9417 | 200 | 0.5410 | 0.5068 | 0.5410 | 0.7355 |
|
| 152 |
+
| No log | 1.9612 | 202 | 0.4834 | 0.5456 | 0.4834 | 0.6952 |
|
| 153 |
+
| No log | 1.9806 | 204 | 0.4564 | 0.5993 | 0.4564 | 0.6756 |
|
| 154 |
+
| No log | 2.0 | 206 | 0.5032 | 0.6130 | 0.5032 | 0.7094 |
|
| 155 |
+
| No log | 2.0194 | 208 | 0.5107 | 0.6141 | 0.5107 | 0.7146 |
|
| 156 |
+
| No log | 2.0388 | 210 | 0.5354 | 0.5934 | 0.5354 | 0.7317 |
|
| 157 |
+
| No log | 2.0583 | 212 | 0.6298 | 0.5544 | 0.6298 | 0.7936 |
|
| 158 |
+
| No log | 2.0777 | 214 | 0.6518 | 0.5299 | 0.6518 | 0.8073 |
|
| 159 |
+
| No log | 2.0971 | 216 | 0.5772 | 0.5484 | 0.5772 | 0.7597 |
|
| 160 |
+
| No log | 2.1165 | 218 | 0.4868 | 0.6097 | 0.4868 | 0.6977 |
|
| 161 |
+
| No log | 2.1359 | 220 | 0.4603 | 0.5497 | 0.4603 | 0.6784 |
|
| 162 |
+
| No log | 2.1553 | 222 | 0.4669 | 0.5136 | 0.4669 | 0.6833 |
|
| 163 |
+
| No log | 2.1748 | 224 | 0.4767 | 0.5825 | 0.4767 | 0.6905 |
|
| 164 |
+
| No log | 2.1942 | 226 | 0.5362 | 0.5868 | 0.5362 | 0.7322 |
|
| 165 |
+
| No log | 2.2136 | 228 | 0.5987 | 0.5293 | 0.5987 | 0.7738 |
|
| 166 |
+
| No log | 2.2330 | 230 | 0.6892 | 0.5273 | 0.6892 | 0.8302 |
|
| 167 |
+
| No log | 2.2524 | 232 | 0.7109 | 0.5452 | 0.7109 | 0.8431 |
|
| 168 |
+
| No log | 2.2718 | 234 | 0.6664 | 0.5634 | 0.6664 | 0.8163 |
|
| 169 |
+
| No log | 2.2913 | 236 | 0.7045 | 0.5180 | 0.7045 | 0.8393 |
|
| 170 |
+
| No log | 2.3107 | 238 | 0.7991 | 0.5335 | 0.7991 | 0.8939 |
|
| 171 |
+
| No log | 2.3301 | 240 | 0.7188 | 0.5624 | 0.7188 | 0.8478 |
|
| 172 |
+
| No log | 2.3495 | 242 | 0.5465 | 0.5943 | 0.5465 | 0.7393 |
|
| 173 |
+
| No log | 2.3689 | 244 | 0.4863 | 0.5975 | 0.4863 | 0.6974 |
|
| 174 |
+
| No log | 2.3883 | 246 | 0.4878 | 0.5633 | 0.4878 | 0.6984 |
|
| 175 |
+
| No log | 2.4078 | 248 | 0.4951 | 0.5247 | 0.4951 | 0.7037 |
|
| 176 |
+
| No log | 2.4272 | 250 | 0.5445 | 0.5491 | 0.5445 | 0.7379 |
|
| 177 |
+
| No log | 2.4466 | 252 | 0.5991 | 0.4937 | 0.5991 | 0.7740 |
|
| 178 |
+
| No log | 2.4660 | 254 | 0.5941 | 0.5084 | 0.5941 | 0.7708 |
|
| 179 |
+
| No log | 2.4854 | 256 | 0.5324 | 0.5057 | 0.5324 | 0.7296 |
|
| 180 |
+
| No log | 2.5049 | 258 | 0.4877 | 0.5353 | 0.4877 | 0.6983 |
|
| 181 |
+
| No log | 2.5243 | 260 | 0.4715 | 0.5469 | 0.4715 | 0.6866 |
|
| 182 |
+
| No log | 2.5437 | 262 | 0.4589 | 0.5627 | 0.4589 | 0.6774 |
|
| 183 |
+
| No log | 2.5631 | 264 | 0.5118 | 0.5565 | 0.5118 | 0.7154 |
|
| 184 |
+
| No log | 2.5825 | 266 | 0.5824 | 0.5223 | 0.5824 | 0.7632 |
|
| 185 |
+
| No log | 2.6019 | 268 | 0.5401 | 0.5565 | 0.5401 | 0.7349 |
|
| 186 |
+
| No log | 2.6214 | 270 | 0.4580 | 0.5610 | 0.4580 | 0.6768 |
|
| 187 |
+
| No log | 2.6408 | 272 | 0.4690 | 0.5792 | 0.4690 | 0.6849 |
|
| 188 |
+
| No log | 2.6602 | 274 | 0.4957 | 0.5878 | 0.4957 | 0.7041 |
|
| 189 |
+
| No log | 2.6796 | 276 | 0.5316 | 0.5752 | 0.5316 | 0.7291 |
|
| 190 |
+
| No log | 2.6990 | 278 | 0.5905 | 0.5645 | 0.5905 | 0.7684 |
|
| 191 |
+
| No log | 2.7184 | 280 | 0.6116 | 0.5303 | 0.6116 | 0.7820 |
|
| 192 |
+
| No log | 2.7379 | 282 | 0.5301 | 0.5694 | 0.5301 | 0.7281 |
|
| 193 |
+
| No log | 2.7573 | 284 | 0.4703 | 0.6349 | 0.4703 | 0.6858 |
|
| 194 |
+
| No log | 2.7767 | 286 | 0.4633 | 0.6324 | 0.4633 | 0.6806 |
|
| 195 |
+
| No log | 2.7961 | 288 | 0.4918 | 0.6007 | 0.4918 | 0.7013 |
|
| 196 |
+
| No log | 2.8155 | 290 | 0.5483 | 0.5627 | 0.5483 | 0.7405 |
|
| 197 |
+
| No log | 2.8350 | 292 | 0.6367 | 0.5160 | 0.6367 | 0.7979 |
|
| 198 |
+
| No log | 2.8544 | 294 | 0.6195 | 0.5578 | 0.6195 | 0.7871 |
|
| 199 |
+
| No log | 2.8738 | 296 | 0.5627 | 0.5896 | 0.5627 | 0.7502 |
|
| 200 |
+
| No log | 2.8932 | 298 | 0.5472 | 0.5927 | 0.5472 | 0.7398 |
|
| 201 |
+
| No log | 2.9126 | 300 | 0.5601 | 0.5869 | 0.5601 | 0.7484 |
|
| 202 |
+
| No log | 2.9320 | 302 | 0.5745 | 0.5934 | 0.5745 | 0.7580 |
|
| 203 |
+
| No log | 2.9515 | 304 | 0.5770 | 0.5821 | 0.5770 | 0.7596 |
|
| 204 |
+
| No log | 2.9709 | 306 | 0.4609 | 0.6320 | 0.4609 | 0.6789 |
|
| 205 |
+
| No log | 2.9903 | 308 | 0.4359 | 0.5807 | 0.4359 | 0.6602 |
|
| 206 |
+
| No log | 3.0097 | 310 | 0.4531 | 0.5308 | 0.4531 | 0.6731 |
|
| 207 |
+
| No log | 3.0291 | 312 | 0.4365 | 0.5746 | 0.4365 | 0.6607 |
|
| 208 |
+
| No log | 3.0485 | 314 | 0.5167 | 0.5513 | 0.5167 | 0.7188 |
|
| 209 |
+
| No log | 3.0680 | 316 | 0.6775 | 0.4924 | 0.6775 | 0.8231 |
|
| 210 |
+
| No log | 3.0874 | 318 | 0.7080 | 0.4916 | 0.7080 | 0.8414 |
|
| 211 |
+
| No log | 3.1068 | 320 | 0.5510 | 0.5634 | 0.5510 | 0.7423 |
|
| 212 |
+
| No log | 3.1262 | 322 | 0.4830 | 0.6149 | 0.4830 | 0.6950 |
|
| 213 |
+
| No log | 3.1456 | 324 | 0.4578 | 0.6345 | 0.4578 | 0.6766 |
|
| 214 |
+
| No log | 3.1650 | 326 | 0.4658 | 0.6258 | 0.4658 | 0.6825 |
|
| 215 |
+
| No log | 3.1845 | 328 | 0.4954 | 0.6346 | 0.4954 | 0.7038 |
|
| 216 |
+
| No log | 3.2039 | 330 | 0.4748 | 0.6427 | 0.4748 | 0.6891 |
|
| 217 |
+
| No log | 3.2233 | 332 | 0.4469 | 0.6646 | 0.4469 | 0.6685 |
|
| 218 |
+
| No log | 3.2427 | 334 | 0.4544 | 0.6455 | 0.4544 | 0.6741 |
|
| 219 |
+
| No log | 3.2621 | 336 | 0.4646 | 0.6187 | 0.4646 | 0.6816 |
|
| 220 |
+
| No log | 3.2816 | 338 | 0.5084 | 0.5853 | 0.5084 | 0.7130 |
|
| 221 |
+
| No log | 3.3010 | 340 | 0.5481 | 0.5621 | 0.5481 | 0.7403 |
|
| 222 |
+
| No log | 3.3204 | 342 | 0.5867 | 0.5422 | 0.5867 | 0.7660 |
|
| 223 |
+
| No log | 3.3398 | 344 | 0.5339 | 0.5650 | 0.5339 | 0.7307 |
|
| 224 |
+
| No log | 3.3592 | 346 | 0.4708 | 0.6416 | 0.4708 | 0.6861 |
|
| 225 |
+
| No log | 3.3786 | 348 | 0.4752 | 0.6357 | 0.4752 | 0.6894 |
|
| 226 |
+
| No log | 3.3981 | 350 | 0.4780 | 0.6276 | 0.4780 | 0.6913 |
|
| 227 |
+
| No log | 3.4175 | 352 | 0.5024 | 0.6132 | 0.5024 | 0.7088 |
|
| 228 |
+
| No log | 3.4369 | 354 | 0.5332 | 0.5940 | 0.5332 | 0.7302 |
|
| 229 |
+
| No log | 3.4563 | 356 | 0.5591 | 0.5682 | 0.5591 | 0.7477 |
|
| 230 |
+
| No log | 3.4757 | 358 | 0.5566 | 0.5704 | 0.5566 | 0.7461 |
|
| 231 |
+
| No log | 3.4951 | 360 | 0.5596 | 0.5456 | 0.5596 | 0.7480 |
|
| 232 |
+
| No log | 3.5146 | 362 | 0.5304 | 0.5464 | 0.5304 | 0.7283 |
|
| 233 |
+
| No log | 3.5340 | 364 | 0.5426 | 0.5552 | 0.5426 | 0.7366 |
|
| 234 |
+
| No log | 3.5534 | 366 | 0.5885 | 0.5402 | 0.5885 | 0.7672 |
|
| 235 |
+
| No log | 3.5728 | 368 | 0.6248 | 0.5048 | 0.6248 | 0.7904 |
|
| 236 |
+
| No log | 3.5922 | 370 | 0.5326 | 0.5680 | 0.5326 | 0.7298 |
|
| 237 |
+
| No log | 3.6117 | 372 | 0.4745 | 0.5689 | 0.4745 | 0.6889 |
|
| 238 |
+
| No log | 3.6311 | 374 | 0.4612 | 0.5776 | 0.4612 | 0.6791 |
|
| 239 |
+
| No log | 3.6505 | 376 | 0.4595 | 0.5968 | 0.4595 | 0.6779 |
|
| 240 |
+
| No log | 3.6699 | 378 | 0.5115 | 0.5590 | 0.5115 | 0.7152 |
|
| 241 |
+
| No log | 3.6893 | 380 | 0.5568 | 0.5329 | 0.5568 | 0.7462 |
|
| 242 |
+
| No log | 3.7087 | 382 | 0.5341 | 0.5713 | 0.5341 | 0.7308 |
|
| 243 |
+
| No log | 3.7282 | 384 | 0.4777 | 0.5978 | 0.4777 | 0.6912 |
|
| 244 |
+
| No log | 3.7476 | 386 | 0.4856 | 0.6393 | 0.4856 | 0.6969 |
|
| 245 |
+
| No log | 3.7670 | 388 | 0.4701 | 0.6397 | 0.4701 | 0.6856 |
|
| 246 |
+
| No log | 3.7864 | 390 | 0.4745 | 0.6210 | 0.4745 | 0.6889 |
|
| 247 |
+
| No log | 3.8058 | 392 | 0.5133 | 0.5870 | 0.5133 | 0.7164 |
|
| 248 |
+
| No log | 3.8252 | 394 | 0.5393 | 0.5845 | 0.5393 | 0.7344 |
|
| 249 |
+
| No log | 3.8447 | 396 | 0.5209 | 0.5874 | 0.5209 | 0.7218 |
|
| 250 |
+
| No log | 3.8641 | 398 | 0.4869 | 0.6136 | 0.4869 | 0.6978 |
|
| 251 |
+
| No log | 3.8835 | 400 | 0.5143 | 0.6148 | 0.5143 | 0.7171 |
|
| 252 |
+
| No log | 3.9029 | 402 | 0.5088 | 0.6156 | 0.5088 | 0.7133 |
|
| 253 |
+
| No log | 3.9223 | 404 | 0.5327 | 0.5760 | 0.5327 | 0.7299 |
|
| 254 |
+
| No log | 3.9417 | 406 | 0.6752 | 0.5536 | 0.6752 | 0.8217 |
|
| 255 |
+
| No log | 3.9612 | 408 | 0.6384 | 0.5615 | 0.6384 | 0.7990 |
|
| 256 |
+
| No log | 3.9806 | 410 | 0.5492 | 0.5368 | 0.5492 | 0.7411 |
|
| 257 |
+
| No log | 4.0 | 412 | 0.5137 | 0.5769 | 0.5137 | 0.7167 |
|
| 258 |
+
| No log | 4.0194 | 414 | 0.4946 | 0.5898 | 0.4946 | 0.7033 |
|
| 259 |
+
| No log | 4.0388 | 416 | 0.5414 | 0.5737 | 0.5414 | 0.7358 |
|
| 260 |
+
| No log | 4.0583 | 418 | 0.7217 | 0.5596 | 0.7217 | 0.8496 |
|
| 261 |
+
| No log | 4.0777 | 420 | 0.7358 | 0.5580 | 0.7358 | 0.8578 |
|
| 262 |
+
| No log | 4.0971 | 422 | 0.6055 | 0.5672 | 0.6055 | 0.7781 |
|
| 263 |
+
| No log | 4.1165 | 424 | 0.5514 | 0.5833 | 0.5514 | 0.7426 |
|
| 264 |
+
| No log | 4.1359 | 426 | 0.5632 | 0.5857 | 0.5632 | 0.7505 |
|
| 265 |
+
| No log | 4.1553 | 428 | 0.5653 | 0.5728 | 0.5653 | 0.7519 |
|
| 266 |
+
| No log | 4.1748 | 430 | 0.7886 | 0.5806 | 0.7886 | 0.8880 |
|
| 267 |
+
| No log | 4.1942 | 432 | 0.9425 | 0.5621 | 0.9425 | 0.9708 |
|
| 268 |
+
| No log | 4.2136 | 434 | 0.7834 | 0.5612 | 0.7834 | 0.8851 |
|
| 269 |
+
| No log | 4.2330 | 436 | 0.5045 | 0.5930 | 0.5045 | 0.7103 |
|
| 270 |
+
| No log | 4.2524 | 438 | 0.4787 | 0.6151 | 0.4787 | 0.6919 |
|
| 271 |
+
| No log | 4.2718 | 440 | 0.4525 | 0.6314 | 0.4525 | 0.6727 |
|
| 272 |
+
| No log | 4.2913 | 442 | 0.5405 | 0.5804 | 0.5405 | 0.7352 |
|
| 273 |
+
| No log | 4.3107 | 444 | 0.7829 | 0.5530 | 0.7829 | 0.8848 |
|
| 274 |
+
| No log | 4.3301 | 446 | 0.7624 | 0.5382 | 0.7624 | 0.8731 |
|
| 275 |
+
| No log | 4.3495 | 448 | 0.5518 | 0.5940 | 0.5518 | 0.7428 |
|
| 276 |
+
| No log | 4.3689 | 450 | 0.4466 | 0.6150 | 0.4466 | 0.6683 |
|
| 277 |
+
| No log | 4.3883 | 452 | 0.4626 | 0.5760 | 0.4626 | 0.6801 |
|
| 278 |
+
| No log | 4.4078 | 454 | 0.4597 | 0.5911 | 0.4597 | 0.6780 |
|
| 279 |
+
| No log | 4.4272 | 456 | 0.4537 | 0.5898 | 0.4537 | 0.6736 |
|
| 280 |
+
| No log | 4.4466 | 458 | 0.4605 | 0.6325 | 0.4605 | 0.6786 |
|
| 281 |
+
| No log | 4.4660 | 460 | 0.4995 | 0.6250 | 0.4995 | 0.7067 |
|
| 282 |
+
| No log | 4.4854 | 462 | 0.4679 | 0.6342 | 0.4679 | 0.6840 |
|
| 283 |
+
| No log | 4.5049 | 464 | 0.4824 | 0.6461 | 0.4824 | 0.6945 |
|
| 284 |
+
| No log | 4.5243 | 466 | 0.5036 | 0.6415 | 0.5036 | 0.7097 |
|
| 285 |
+
| No log | 4.5437 | 468 | 0.4977 | 0.6382 | 0.4977 | 0.7055 |
|
| 286 |
+
| No log | 4.5631 | 470 | 0.5532 | 0.6175 | 0.5532 | 0.7438 |
|
| 287 |
+
| No log | 4.5825 | 472 | 0.5259 | 0.5839 | 0.5259 | 0.7252 |
|
| 288 |
+
| No log | 4.6019 | 474 | 0.5735 | 0.5797 | 0.5735 | 0.7573 |
|
| 289 |
+
| No log | 4.6214 | 476 | 0.6616 | 0.5669 | 0.6616 | 0.8134 |
|
| 290 |
+
| No log | 4.6408 | 478 | 0.7244 | 0.5504 | 0.7244 | 0.8511 |
|
| 291 |
+
| No log | 4.6602 | 480 | 0.6635 | 0.5653 | 0.6635 | 0.8145 |
|
| 292 |
+
| No log | 4.6796 | 482 | 0.5177 | 0.5902 | 0.5177 | 0.7195 |
|
| 293 |
+
| No log | 4.6990 | 484 | 0.4558 | 0.5988 | 0.4558 | 0.6751 |
|
| 294 |
+
| No log | 4.7184 | 486 | 0.4547 | 0.5895 | 0.4547 | 0.6743 |
|
| 295 |
+
| No log | 4.7379 | 488 | 0.4688 | 0.5756 | 0.4688 | 0.6847 |
|
| 296 |
+
| No log | 4.7573 | 490 | 0.5761 | 0.5615 | 0.5761 | 0.7590 |
|
| 297 |
+
| No log | 4.7767 | 492 | 0.6651 | 0.5222 | 0.6651 | 0.8156 |
|
| 298 |
+
| No log | 4.7961 | 494 | 0.6016 | 0.5245 | 0.6016 | 0.7756 |
|
| 299 |
+
| No log | 4.8155 | 496 | 0.5011 | 0.5653 | 0.5011 | 0.7079 |
|
| 300 |
+
| No log | 4.8350 | 498 | 0.4574 | 0.5667 | 0.4574 | 0.6763 |
|
| 301 |
+
| 0.53 | 4.8544 | 500 | 0.4520 | 0.5761 | 0.4520 | 0.6723 |
|
| 302 |
+
| 0.53 | 4.8738 | 502 | 0.4726 | 0.5993 | 0.4726 | 0.6874 |
|
| 303 |
+
| 0.53 | 4.8932 | 504 | 0.5501 | 0.5582 | 0.5501 | 0.7417 |
|
| 304 |
+
| 0.53 | 4.9126 | 506 | 0.5831 | 0.5671 | 0.5831 | 0.7636 |
|
| 305 |
+
| 0.53 | 4.9320 | 508 | 0.5097 | 0.5817 | 0.5097 | 0.7139 |
|
| 306 |
+
| 0.53 | 4.9515 | 510 | 0.5021 | 0.6048 | 0.5021 | 0.7086 |
|
| 307 |
+
| 0.53 | 4.9709 | 512 | 0.5653 | 0.5900 | 0.5653 | 0.7519 |
|
| 308 |
+
| 0.53 | 4.9903 | 514 | 0.6278 | 0.5830 | 0.6278 | 0.7924 |
|
| 309 |
+
| 0.53 | 5.0097 | 516 | 0.6706 | 0.5531 | 0.6706 | 0.8189 |
|
| 310 |
+
| 0.53 | 5.0291 | 518 | 0.5891 | 0.5773 | 0.5891 | 0.7676 |
|
| 311 |
+
| 0.53 | 5.0485 | 520 | 0.4875 | 0.6380 | 0.4875 | 0.6982 |
|
| 312 |
+
| 0.53 | 5.0680 | 522 | 0.4882 | 0.6250 | 0.4882 | 0.6987 |
|
| 313 |
+
| 0.53 | 5.0874 | 524 | 0.5620 | 0.5813 | 0.5620 | 0.7497 |
|
| 314 |
+
| 0.53 | 5.1068 | 526 | 0.6514 | 0.5633 | 0.6514 | 0.8071 |
|
| 315 |
+
| 0.53 | 5.1262 | 528 | 0.6162 | 0.5737 | 0.6162 | 0.7850 |
|
| 316 |
+
| 0.53 | 5.1456 | 530 | 0.5488 | 0.5685 | 0.5488 | 0.7408 |
|
| 317 |
+
| 0.53 | 5.1650 | 532 | 0.5820 | 0.5751 | 0.5820 | 0.7629 |
|
| 318 |
+
| 0.53 | 5.1845 | 534 | 0.5716 | 0.5757 | 0.5716 | 0.7560 |
|
| 319 |
+
|
| 320 |
+
|
| 321 |
+
### Framework versions
|
| 322 |
+
|
| 323 |
+
- Transformers 4.44.2
|
| 324 |
+
- Pytorch 2.4.0+cu118
|
| 325 |
+
- Datasets 2.21.0
|
| 326 |
+
- 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 sha256:3ef071b4ede4d43efece21691b8e5c5e25af8139005224ac74c7969482ae6251
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b295a7dbc712ea5706aa2240b4c3bded8bc4995d825e7617657d925b93837261
|
| 3 |
+
size 5240
|