Training in progress, step 500
Browse files- README.md +317 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k13_task2_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_k13_task2_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: 0.8716
|
| 19 |
+
- Qwk: 0.5029
|
| 20 |
+
- Mse: 0.8716
|
| 21 |
+
- Rmse: 0.9336
|
| 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 | 0.0270 | 2 | 4.5371 | 0.0163 | 4.5371 | 2.1301 |
|
| 53 |
+
| No log | 0.0541 | 4 | 2.5560 | 0.0554 | 2.5560 | 1.5988 |
|
| 54 |
+
| No log | 0.0811 | 6 | 1.6001 | 0.0504 | 1.6001 | 1.2650 |
|
| 55 |
+
| No log | 0.1081 | 8 | 1.2120 | 0.1517 | 1.2120 | 1.1009 |
|
| 56 |
+
| No log | 0.1351 | 10 | 1.1295 | 0.2233 | 1.1295 | 1.0628 |
|
| 57 |
+
| No log | 0.1622 | 12 | 1.1435 | 0.2023 | 1.1435 | 1.0694 |
|
| 58 |
+
| No log | 0.1892 | 14 | 1.1249 | 0.1773 | 1.1249 | 1.0606 |
|
| 59 |
+
| No log | 0.2162 | 16 | 1.0802 | 0.2257 | 1.0802 | 1.0393 |
|
| 60 |
+
| No log | 0.2432 | 18 | 1.0532 | 0.2731 | 1.0532 | 1.0262 |
|
| 61 |
+
| No log | 0.2703 | 20 | 1.0315 | 0.3404 | 1.0315 | 1.0156 |
|
| 62 |
+
| No log | 0.2973 | 22 | 1.0817 | 0.3411 | 1.0817 | 1.0400 |
|
| 63 |
+
| No log | 0.3243 | 24 | 1.1050 | 0.2515 | 1.1050 | 1.0512 |
|
| 64 |
+
| No log | 0.3514 | 26 | 0.9852 | 0.4075 | 0.9852 | 0.9926 |
|
| 65 |
+
| No log | 0.3784 | 28 | 1.0752 | 0.3955 | 1.0752 | 1.0369 |
|
| 66 |
+
| No log | 0.4054 | 30 | 1.6314 | 0.1512 | 1.6314 | 1.2773 |
|
| 67 |
+
| No log | 0.4324 | 32 | 1.5090 | 0.1448 | 1.5090 | 1.2284 |
|
| 68 |
+
| No log | 0.4595 | 34 | 1.0883 | 0.3086 | 1.0883 | 1.0432 |
|
| 69 |
+
| No log | 0.4865 | 36 | 1.0113 | 0.3151 | 1.0113 | 1.0056 |
|
| 70 |
+
| No log | 0.5135 | 38 | 0.9780 | 0.3462 | 0.9780 | 0.9890 |
|
| 71 |
+
| No log | 0.5405 | 40 | 1.0241 | 0.3798 | 1.0241 | 1.0120 |
|
| 72 |
+
| No log | 0.5676 | 42 | 0.9280 | 0.4945 | 0.9280 | 0.9633 |
|
| 73 |
+
| No log | 0.5946 | 44 | 0.9652 | 0.3816 | 0.9652 | 0.9824 |
|
| 74 |
+
| No log | 0.6216 | 46 | 1.0881 | 0.4414 | 1.0881 | 1.0431 |
|
| 75 |
+
| No log | 0.6486 | 48 | 1.0700 | 0.4722 | 1.0700 | 1.0344 |
|
| 76 |
+
| No log | 0.6757 | 50 | 0.8942 | 0.4726 | 0.8942 | 0.9456 |
|
| 77 |
+
| No log | 0.7027 | 52 | 0.9880 | 0.4057 | 0.9880 | 0.9940 |
|
| 78 |
+
| No log | 0.7297 | 54 | 1.0929 | 0.3620 | 1.0929 | 1.0454 |
|
| 79 |
+
| No log | 0.7568 | 56 | 1.0165 | 0.4776 | 1.0165 | 1.0082 |
|
| 80 |
+
| No log | 0.7838 | 58 | 0.7943 | 0.6023 | 0.7943 | 0.8912 |
|
| 81 |
+
| No log | 0.8108 | 60 | 0.9954 | 0.5192 | 0.9954 | 0.9977 |
|
| 82 |
+
| No log | 0.8378 | 62 | 1.1706 | 0.5409 | 1.1706 | 1.0819 |
|
| 83 |
+
| No log | 0.8649 | 64 | 0.9111 | 0.5077 | 0.9111 | 0.9545 |
|
| 84 |
+
| No log | 0.8919 | 66 | 0.7321 | 0.5797 | 0.7321 | 0.8556 |
|
| 85 |
+
| No log | 0.9189 | 68 | 0.8754 | 0.5388 | 0.8754 | 0.9356 |
|
| 86 |
+
| No log | 0.9459 | 70 | 1.1108 | 0.3741 | 1.1108 | 1.0540 |
|
| 87 |
+
| No log | 0.9730 | 72 | 1.0038 | 0.4329 | 1.0038 | 1.0019 |
|
| 88 |
+
| No log | 1.0 | 74 | 0.7634 | 0.6117 | 0.7634 | 0.8737 |
|
| 89 |
+
| No log | 1.0270 | 76 | 0.7251 | 0.6175 | 0.7251 | 0.8515 |
|
| 90 |
+
| No log | 1.0541 | 78 | 0.8743 | 0.6073 | 0.8743 | 0.9351 |
|
| 91 |
+
| No log | 1.0811 | 80 | 0.8879 | 0.5930 | 0.8879 | 0.9423 |
|
| 92 |
+
| No log | 1.1081 | 82 | 0.7728 | 0.6073 | 0.7728 | 0.8791 |
|
| 93 |
+
| No log | 1.1351 | 84 | 0.6930 | 0.6748 | 0.6930 | 0.8325 |
|
| 94 |
+
| No log | 1.1622 | 86 | 0.7908 | 0.5920 | 0.7908 | 0.8892 |
|
| 95 |
+
| No log | 1.1892 | 88 | 0.7706 | 0.5655 | 0.7706 | 0.8778 |
|
| 96 |
+
| No log | 1.2162 | 90 | 0.6836 | 0.6176 | 0.6836 | 0.8268 |
|
| 97 |
+
| No log | 1.2432 | 92 | 0.6811 | 0.6019 | 0.6811 | 0.8253 |
|
| 98 |
+
| No log | 1.2703 | 94 | 0.7016 | 0.6025 | 0.7016 | 0.8376 |
|
| 99 |
+
| No log | 1.2973 | 96 | 0.8474 | 0.4621 | 0.8474 | 0.9205 |
|
| 100 |
+
| No log | 1.3243 | 98 | 0.7566 | 0.5840 | 0.7566 | 0.8698 |
|
| 101 |
+
| No log | 1.3514 | 100 | 0.6996 | 0.6272 | 0.6996 | 0.8364 |
|
| 102 |
+
| No log | 1.3784 | 102 | 0.9095 | 0.6102 | 0.9095 | 0.9537 |
|
| 103 |
+
| No log | 1.4054 | 104 | 1.1709 | 0.5241 | 1.1709 | 1.0821 |
|
| 104 |
+
| No log | 1.4324 | 106 | 1.0962 | 0.5579 | 1.0962 | 1.0470 |
|
| 105 |
+
| No log | 1.4595 | 108 | 0.8729 | 0.6146 | 0.8729 | 0.9343 |
|
| 106 |
+
| No log | 1.4865 | 110 | 0.7288 | 0.6443 | 0.7288 | 0.8537 |
|
| 107 |
+
| No log | 1.5135 | 112 | 0.7437 | 0.6413 | 0.7437 | 0.8624 |
|
| 108 |
+
| No log | 1.5405 | 114 | 0.8208 | 0.5733 | 0.8208 | 0.9060 |
|
| 109 |
+
| No log | 1.5676 | 116 | 0.7586 | 0.5757 | 0.7586 | 0.8710 |
|
| 110 |
+
| No log | 1.5946 | 118 | 0.7500 | 0.6004 | 0.7500 | 0.8660 |
|
| 111 |
+
| No log | 1.6216 | 120 | 0.6728 | 0.6332 | 0.6728 | 0.8202 |
|
| 112 |
+
| No log | 1.6486 | 122 | 0.6779 | 0.6061 | 0.6779 | 0.8233 |
|
| 113 |
+
| No log | 1.6757 | 124 | 0.6897 | 0.5971 | 0.6897 | 0.8305 |
|
| 114 |
+
| No log | 1.7027 | 126 | 0.7158 | 0.5963 | 0.7158 | 0.8461 |
|
| 115 |
+
| No log | 1.7297 | 128 | 0.7076 | 0.6746 | 0.7076 | 0.8412 |
|
| 116 |
+
| No log | 1.7568 | 130 | 0.8323 | 0.5766 | 0.8323 | 0.9123 |
|
| 117 |
+
| No log | 1.7838 | 132 | 1.0607 | 0.5199 | 1.0607 | 1.0299 |
|
| 118 |
+
| No log | 1.8108 | 134 | 1.1491 | 0.5028 | 1.1491 | 1.0720 |
|
| 119 |
+
| No log | 1.8378 | 136 | 0.9945 | 0.5504 | 0.9945 | 0.9972 |
|
| 120 |
+
| No log | 1.8649 | 138 | 0.8189 | 0.5779 | 0.8189 | 0.9049 |
|
| 121 |
+
| No log | 1.8919 | 140 | 0.6831 | 0.6254 | 0.6831 | 0.8265 |
|
| 122 |
+
| No log | 1.9189 | 142 | 0.9512 | 0.4218 | 0.9512 | 0.9753 |
|
| 123 |
+
| No log | 1.9459 | 144 | 0.9517 | 0.4974 | 0.9517 | 0.9756 |
|
| 124 |
+
| No log | 1.9730 | 146 | 0.8734 | 0.5134 | 0.8734 | 0.9346 |
|
| 125 |
+
| No log | 2.0 | 148 | 0.7630 | 0.5551 | 0.7630 | 0.8735 |
|
| 126 |
+
| No log | 2.0270 | 150 | 0.7278 | 0.6244 | 0.7278 | 0.8531 |
|
| 127 |
+
| No log | 2.0541 | 152 | 0.8882 | 0.5959 | 0.8882 | 0.9424 |
|
| 128 |
+
| No log | 2.0811 | 154 | 0.9066 | 0.5444 | 0.9066 | 0.9522 |
|
| 129 |
+
| No log | 2.1081 | 156 | 0.8712 | 0.5576 | 0.8712 | 0.9334 |
|
| 130 |
+
| No log | 2.1351 | 158 | 0.7476 | 0.5959 | 0.7476 | 0.8646 |
|
| 131 |
+
| No log | 2.1622 | 160 | 0.7186 | 0.5553 | 0.7186 | 0.8477 |
|
| 132 |
+
| No log | 2.1892 | 162 | 0.7320 | 0.6154 | 0.7320 | 0.8555 |
|
| 133 |
+
| No log | 2.2162 | 164 | 0.8252 | 0.5766 | 0.8252 | 0.9084 |
|
| 134 |
+
| No log | 2.2432 | 166 | 0.9275 | 0.5614 | 0.9275 | 0.9631 |
|
| 135 |
+
| No log | 2.2703 | 168 | 0.9940 | 0.4977 | 0.9940 | 0.9970 |
|
| 136 |
+
| No log | 2.2973 | 170 | 0.8667 | 0.5601 | 0.8667 | 0.9309 |
|
| 137 |
+
| No log | 2.3243 | 172 | 0.7207 | 0.5898 | 0.7207 | 0.8489 |
|
| 138 |
+
| No log | 2.3514 | 174 | 0.6771 | 0.6485 | 0.6771 | 0.8229 |
|
| 139 |
+
| No log | 2.3784 | 176 | 0.7257 | 0.5440 | 0.7257 | 0.8519 |
|
| 140 |
+
| No log | 2.4054 | 178 | 0.6990 | 0.5505 | 0.6990 | 0.8361 |
|
| 141 |
+
| No log | 2.4324 | 180 | 0.6516 | 0.6386 | 0.6516 | 0.8072 |
|
| 142 |
+
| No log | 2.4595 | 182 | 0.7629 | 0.5947 | 0.7629 | 0.8734 |
|
| 143 |
+
| No log | 2.4865 | 184 | 1.2327 | 0.5247 | 1.2327 | 1.1103 |
|
| 144 |
+
| No log | 2.5135 | 186 | 1.4917 | 0.4750 | 1.4917 | 1.2214 |
|
| 145 |
+
| No log | 2.5405 | 188 | 1.3277 | 0.4852 | 1.3277 | 1.1523 |
|
| 146 |
+
| No log | 2.5676 | 190 | 1.0093 | 0.4885 | 1.0093 | 1.0046 |
|
| 147 |
+
| No log | 2.5946 | 192 | 0.7737 | 0.5895 | 0.7737 | 0.8796 |
|
| 148 |
+
| No log | 2.6216 | 194 | 0.9693 | 0.4153 | 0.9693 | 0.9845 |
|
| 149 |
+
| No log | 2.6486 | 196 | 1.3371 | 0.2616 | 1.3371 | 1.1563 |
|
| 150 |
+
| No log | 2.6757 | 198 | 1.3048 | 0.2278 | 1.3048 | 1.1423 |
|
| 151 |
+
| No log | 2.7027 | 200 | 0.9643 | 0.4225 | 0.9643 | 0.9820 |
|
| 152 |
+
| No log | 2.7297 | 202 | 0.8673 | 0.4852 | 0.8673 | 0.9313 |
|
| 153 |
+
| No log | 2.7568 | 204 | 1.0356 | 0.4841 | 1.0356 | 1.0176 |
|
| 154 |
+
| No log | 2.7838 | 206 | 1.1451 | 0.4505 | 1.1451 | 1.0701 |
|
| 155 |
+
| No log | 2.8108 | 208 | 1.0730 | 0.4052 | 1.0730 | 1.0359 |
|
| 156 |
+
| No log | 2.8378 | 210 | 0.8878 | 0.5028 | 0.8878 | 0.9422 |
|
| 157 |
+
| No log | 2.8649 | 212 | 0.8487 | 0.4976 | 0.8487 | 0.9212 |
|
| 158 |
+
| No log | 2.8919 | 214 | 0.8341 | 0.4783 | 0.8341 | 0.9133 |
|
| 159 |
+
| No log | 2.9189 | 216 | 0.7860 | 0.5520 | 0.7860 | 0.8866 |
|
| 160 |
+
| No log | 2.9459 | 218 | 0.7661 | 0.5779 | 0.7661 | 0.8753 |
|
| 161 |
+
| No log | 2.9730 | 220 | 0.7672 | 0.5382 | 0.7672 | 0.8759 |
|
| 162 |
+
| No log | 3.0 | 222 | 0.8128 | 0.5022 | 0.8128 | 0.9016 |
|
| 163 |
+
| No log | 3.0270 | 224 | 0.7893 | 0.5219 | 0.7893 | 0.8885 |
|
| 164 |
+
| No log | 3.0541 | 226 | 0.7408 | 0.5143 | 0.7408 | 0.8607 |
|
| 165 |
+
| No log | 3.0811 | 228 | 0.7901 | 0.5649 | 0.7901 | 0.8889 |
|
| 166 |
+
| No log | 3.1081 | 230 | 0.8319 | 0.5513 | 0.8319 | 0.9121 |
|
| 167 |
+
| No log | 3.1351 | 232 | 0.8227 | 0.5691 | 0.8227 | 0.9070 |
|
| 168 |
+
| No log | 3.1622 | 234 | 0.8380 | 0.5691 | 0.8380 | 0.9154 |
|
| 169 |
+
| No log | 3.1892 | 236 | 0.7987 | 0.6101 | 0.7987 | 0.8937 |
|
| 170 |
+
| No log | 3.2162 | 238 | 0.8035 | 0.5712 | 0.8035 | 0.8964 |
|
| 171 |
+
| No log | 3.2432 | 240 | 0.8619 | 0.5690 | 0.8619 | 0.9284 |
|
| 172 |
+
| No log | 3.2703 | 242 | 0.8910 | 0.5794 | 0.8910 | 0.9439 |
|
| 173 |
+
| No log | 3.2973 | 244 | 0.9367 | 0.5794 | 0.9367 | 0.9678 |
|
| 174 |
+
| No log | 3.3243 | 246 | 1.0302 | 0.5626 | 1.0302 | 1.0150 |
|
| 175 |
+
| No log | 3.3514 | 248 | 1.0324 | 0.5750 | 1.0324 | 1.0161 |
|
| 176 |
+
| No log | 3.3784 | 250 | 1.1077 | 0.4482 | 1.1077 | 1.0525 |
|
| 177 |
+
| No log | 3.4054 | 252 | 1.0552 | 0.4300 | 1.0552 | 1.0272 |
|
| 178 |
+
| No log | 3.4324 | 254 | 0.9644 | 0.3785 | 0.9644 | 0.9820 |
|
| 179 |
+
| No log | 3.4595 | 256 | 0.8626 | 0.3975 | 0.8626 | 0.9288 |
|
| 180 |
+
| No log | 3.4865 | 258 | 0.8377 | 0.5202 | 0.8377 | 0.9152 |
|
| 181 |
+
| No log | 3.5135 | 260 | 0.7792 | 0.5892 | 0.7792 | 0.8827 |
|
| 182 |
+
| No log | 3.5405 | 262 | 0.7642 | 0.5938 | 0.7642 | 0.8742 |
|
| 183 |
+
| No log | 3.5676 | 264 | 0.7789 | 0.5216 | 0.7789 | 0.8825 |
|
| 184 |
+
| No log | 3.5946 | 266 | 0.8036 | 0.4508 | 0.8036 | 0.8964 |
|
| 185 |
+
| No log | 3.6216 | 268 | 0.8728 | 0.5611 | 0.8728 | 0.9342 |
|
| 186 |
+
| No log | 3.6486 | 270 | 0.9103 | 0.5920 | 0.9103 | 0.9541 |
|
| 187 |
+
| No log | 3.6757 | 272 | 0.9134 | 0.5814 | 0.9134 | 0.9557 |
|
| 188 |
+
| No log | 3.7027 | 274 | 0.8663 | 0.5836 | 0.8663 | 0.9308 |
|
| 189 |
+
| No log | 3.7297 | 276 | 0.8058 | 0.6498 | 0.8058 | 0.8977 |
|
| 190 |
+
| No log | 3.7568 | 278 | 0.8327 | 0.5228 | 0.8327 | 0.9125 |
|
| 191 |
+
| No log | 3.7838 | 280 | 0.8827 | 0.4458 | 0.8827 | 0.9395 |
|
| 192 |
+
| No log | 3.8108 | 282 | 0.8608 | 0.5291 | 0.8608 | 0.9278 |
|
| 193 |
+
| No log | 3.8378 | 284 | 0.8920 | 0.5055 | 0.8920 | 0.9444 |
|
| 194 |
+
| No log | 3.8649 | 286 | 0.9640 | 0.4959 | 0.9640 | 0.9818 |
|
| 195 |
+
| No log | 3.8919 | 288 | 1.0107 | 0.4615 | 1.0107 | 1.0053 |
|
| 196 |
+
| No log | 3.9189 | 290 | 0.9590 | 0.3771 | 0.9590 | 0.9793 |
|
| 197 |
+
| No log | 3.9459 | 292 | 0.9251 | 0.3847 | 0.9251 | 0.9618 |
|
| 198 |
+
| No log | 3.9730 | 294 | 0.9246 | 0.4065 | 0.9246 | 0.9616 |
|
| 199 |
+
| No log | 4.0 | 296 | 0.9350 | 0.4519 | 0.9350 | 0.9669 |
|
| 200 |
+
| No log | 4.0270 | 298 | 0.8490 | 0.4785 | 0.8490 | 0.9214 |
|
| 201 |
+
| No log | 4.0541 | 300 | 0.7567 | 0.5415 | 0.7567 | 0.8699 |
|
| 202 |
+
| No log | 4.0811 | 302 | 0.7759 | 0.5451 | 0.7759 | 0.8809 |
|
| 203 |
+
| No log | 4.1081 | 304 | 0.7793 | 0.5575 | 0.7793 | 0.8828 |
|
| 204 |
+
| No log | 4.1351 | 306 | 0.7175 | 0.6022 | 0.7175 | 0.8471 |
|
| 205 |
+
| No log | 4.1622 | 308 | 0.7160 | 0.5713 | 0.7160 | 0.8461 |
|
| 206 |
+
| No log | 4.1892 | 310 | 0.9105 | 0.5750 | 0.9105 | 0.9542 |
|
| 207 |
+
| No log | 4.2162 | 312 | 1.0611 | 0.5273 | 1.0611 | 1.0301 |
|
| 208 |
+
| No log | 4.2432 | 314 | 0.9984 | 0.5659 | 0.9984 | 0.9992 |
|
| 209 |
+
| No log | 4.2703 | 316 | 0.8245 | 0.5669 | 0.8245 | 0.9080 |
|
| 210 |
+
| No log | 4.2973 | 318 | 0.6982 | 0.6687 | 0.6982 | 0.8356 |
|
| 211 |
+
| No log | 4.3243 | 320 | 0.6927 | 0.6402 | 0.6927 | 0.8323 |
|
| 212 |
+
| No log | 4.3514 | 322 | 0.7178 | 0.6585 | 0.7178 | 0.8472 |
|
| 213 |
+
| No log | 4.3784 | 324 | 0.8427 | 0.5466 | 0.8427 | 0.9180 |
|
| 214 |
+
| No log | 4.4054 | 326 | 0.9153 | 0.5533 | 0.9153 | 0.9567 |
|
| 215 |
+
| No log | 4.4324 | 328 | 0.9198 | 0.5893 | 0.9198 | 0.9591 |
|
| 216 |
+
| No log | 4.4595 | 330 | 0.8525 | 0.5793 | 0.8525 | 0.9233 |
|
| 217 |
+
| No log | 4.4865 | 332 | 0.7889 | 0.5390 | 0.7889 | 0.8882 |
|
| 218 |
+
| No log | 4.5135 | 334 | 0.7401 | 0.5302 | 0.7401 | 0.8603 |
|
| 219 |
+
| No log | 4.5405 | 336 | 0.7346 | 0.5902 | 0.7346 | 0.8571 |
|
| 220 |
+
| No log | 4.5676 | 338 | 0.7384 | 0.5923 | 0.7384 | 0.8593 |
|
| 221 |
+
| No log | 4.5946 | 340 | 0.7445 | 0.5848 | 0.7445 | 0.8628 |
|
| 222 |
+
| No log | 4.6216 | 342 | 0.8023 | 0.5947 | 0.8023 | 0.8957 |
|
| 223 |
+
| No log | 4.6486 | 344 | 0.9334 | 0.5766 | 0.9334 | 0.9661 |
|
| 224 |
+
| No log | 4.6757 | 346 | 1.0010 | 0.6170 | 1.0010 | 1.0005 |
|
| 225 |
+
| No log | 4.7027 | 348 | 0.9969 | 0.6023 | 0.9969 | 0.9984 |
|
| 226 |
+
| No log | 4.7297 | 350 | 0.9298 | 0.5926 | 0.9298 | 0.9643 |
|
| 227 |
+
| No log | 4.7568 | 352 | 0.7885 | 0.5562 | 0.7885 | 0.8880 |
|
| 228 |
+
| No log | 4.7838 | 354 | 0.7309 | 0.5483 | 0.7309 | 0.8549 |
|
| 229 |
+
| No log | 4.8108 | 356 | 0.7337 | 0.5358 | 0.7337 | 0.8566 |
|
| 230 |
+
| No log | 4.8378 | 358 | 0.7677 | 0.6319 | 0.7677 | 0.8762 |
|
| 231 |
+
| No log | 4.8649 | 360 | 0.8895 | 0.5531 | 0.8895 | 0.9431 |
|
| 232 |
+
| No log | 4.8919 | 362 | 0.9440 | 0.5509 | 0.9440 | 0.9716 |
|
| 233 |
+
| No log | 4.9189 | 364 | 0.9707 | 0.5649 | 0.9707 | 0.9853 |
|
| 234 |
+
| No log | 4.9459 | 366 | 0.8808 | 0.5509 | 0.8808 | 0.9385 |
|
| 235 |
+
| No log | 4.9730 | 368 | 0.7760 | 0.5218 | 0.7760 | 0.8809 |
|
| 236 |
+
| No log | 5.0 | 370 | 0.7185 | 0.5805 | 0.7185 | 0.8476 |
|
| 237 |
+
| No log | 5.0270 | 372 | 0.7155 | 0.5458 | 0.7155 | 0.8459 |
|
| 238 |
+
| No log | 5.0541 | 374 | 0.7269 | 0.4964 | 0.7269 | 0.8526 |
|
| 239 |
+
| No log | 5.0811 | 376 | 0.7336 | 0.4933 | 0.7336 | 0.8565 |
|
| 240 |
+
| No log | 5.1081 | 378 | 0.7413 | 0.5336 | 0.7413 | 0.8610 |
|
| 241 |
+
| No log | 5.1351 | 380 | 0.7483 | 0.5131 | 0.7483 | 0.8651 |
|
| 242 |
+
| No log | 5.1622 | 382 | 0.7711 | 0.5968 | 0.7711 | 0.8781 |
|
| 243 |
+
| No log | 5.1892 | 384 | 0.7645 | 0.6097 | 0.7645 | 0.8744 |
|
| 244 |
+
| No log | 5.2162 | 386 | 0.7516 | 0.5559 | 0.7516 | 0.8669 |
|
| 245 |
+
| No log | 5.2432 | 388 | 0.7575 | 0.5873 | 0.7575 | 0.8703 |
|
| 246 |
+
| No log | 5.2703 | 390 | 0.7799 | 0.5720 | 0.7799 | 0.8831 |
|
| 247 |
+
| No log | 5.2973 | 392 | 0.7933 | 0.5806 | 0.7933 | 0.8907 |
|
| 248 |
+
| No log | 5.3243 | 394 | 0.8021 | 0.5562 | 0.8021 | 0.8956 |
|
| 249 |
+
| No log | 5.3514 | 396 | 0.7699 | 0.5279 | 0.7699 | 0.8774 |
|
| 250 |
+
| No log | 5.3784 | 398 | 0.7659 | 0.4385 | 0.7659 | 0.8752 |
|
| 251 |
+
| No log | 5.4054 | 400 | 0.7648 | 0.4479 | 0.7648 | 0.8745 |
|
| 252 |
+
| No log | 5.4324 | 402 | 0.7623 | 0.4728 | 0.7623 | 0.8731 |
|
| 253 |
+
| No log | 5.4595 | 404 | 0.7528 | 0.4620 | 0.7528 | 0.8676 |
|
| 254 |
+
| No log | 5.4865 | 406 | 0.7600 | 0.4902 | 0.7600 | 0.8718 |
|
| 255 |
+
| No log | 5.5135 | 408 | 0.7744 | 0.5610 | 0.7744 | 0.8800 |
|
| 256 |
+
| No log | 5.5405 | 410 | 0.8333 | 0.5448 | 0.8333 | 0.9129 |
|
| 257 |
+
| No log | 5.5676 | 412 | 0.8461 | 0.5515 | 0.8461 | 0.9199 |
|
| 258 |
+
| No log | 5.5946 | 414 | 0.9113 | 0.5830 | 0.9113 | 0.9546 |
|
| 259 |
+
| No log | 5.6216 | 416 | 0.8955 | 0.5830 | 0.8955 | 0.9463 |
|
| 260 |
+
| No log | 5.6486 | 418 | 0.8003 | 0.5865 | 0.8003 | 0.8946 |
|
| 261 |
+
| No log | 5.6757 | 420 | 0.7484 | 0.5611 | 0.7484 | 0.8651 |
|
| 262 |
+
| No log | 5.7027 | 422 | 0.7190 | 0.5722 | 0.7190 | 0.8480 |
|
| 263 |
+
| No log | 5.7297 | 424 | 0.7227 | 0.5611 | 0.7227 | 0.8501 |
|
| 264 |
+
| No log | 5.7568 | 426 | 0.7155 | 0.5815 | 0.7155 | 0.8459 |
|
| 265 |
+
| No log | 5.7838 | 428 | 0.7279 | 0.5585 | 0.7279 | 0.8531 |
|
| 266 |
+
| No log | 5.8108 | 430 | 0.7363 | 0.5585 | 0.7363 | 0.8581 |
|
| 267 |
+
| No log | 5.8378 | 432 | 0.6867 | 0.5585 | 0.6867 | 0.8287 |
|
| 268 |
+
| No log | 5.8649 | 434 | 0.6314 | 0.6015 | 0.6314 | 0.7946 |
|
| 269 |
+
| No log | 5.8919 | 436 | 0.6188 | 0.6698 | 0.6188 | 0.7866 |
|
| 270 |
+
| No log | 5.9189 | 438 | 0.6240 | 0.6252 | 0.6240 | 0.7899 |
|
| 271 |
+
| No log | 5.9459 | 440 | 0.6325 | 0.6242 | 0.6325 | 0.7953 |
|
| 272 |
+
| No log | 5.9730 | 442 | 0.6728 | 0.4824 | 0.6728 | 0.8203 |
|
| 273 |
+
| No log | 6.0 | 444 | 0.7177 | 0.4879 | 0.7177 | 0.8472 |
|
| 274 |
+
| No log | 6.0270 | 446 | 0.7326 | 0.4879 | 0.7326 | 0.8559 |
|
| 275 |
+
| No log | 6.0541 | 448 | 0.7244 | 0.5014 | 0.7244 | 0.8511 |
|
| 276 |
+
| No log | 6.0811 | 450 | 0.6921 | 0.5524 | 0.6921 | 0.8319 |
|
| 277 |
+
| No log | 6.1081 | 452 | 0.6703 | 0.5648 | 0.6703 | 0.8187 |
|
| 278 |
+
| No log | 6.1351 | 454 | 0.6643 | 0.5770 | 0.6643 | 0.8151 |
|
| 279 |
+
| No log | 6.1622 | 456 | 0.6828 | 0.5716 | 0.6828 | 0.8263 |
|
| 280 |
+
| No log | 6.1892 | 458 | 0.7015 | 0.5543 | 0.7015 | 0.8376 |
|
| 281 |
+
| No log | 6.2162 | 460 | 0.7485 | 0.5991 | 0.7485 | 0.8652 |
|
| 282 |
+
| No log | 6.2432 | 462 | 0.7735 | 0.5991 | 0.7735 | 0.8795 |
|
| 283 |
+
| No log | 6.2703 | 464 | 0.7674 | 0.5991 | 0.7674 | 0.8760 |
|
| 284 |
+
| No log | 6.2973 | 466 | 0.7636 | 0.5991 | 0.7636 | 0.8739 |
|
| 285 |
+
| No log | 6.3243 | 468 | 0.7911 | 0.6154 | 0.7911 | 0.8894 |
|
| 286 |
+
| No log | 6.3514 | 470 | 0.7887 | 0.6154 | 0.7887 | 0.8881 |
|
| 287 |
+
| No log | 6.3784 | 472 | 0.7865 | 0.6038 | 0.7865 | 0.8868 |
|
| 288 |
+
| No log | 6.4054 | 474 | 0.7523 | 0.5905 | 0.7523 | 0.8673 |
|
| 289 |
+
| No log | 6.4324 | 476 | 0.7298 | 0.5727 | 0.7298 | 0.8543 |
|
| 290 |
+
| No log | 6.4595 | 478 | 0.7459 | 0.5424 | 0.7459 | 0.8636 |
|
| 291 |
+
| No log | 6.4865 | 480 | 0.7824 | 0.5246 | 0.7824 | 0.8846 |
|
| 292 |
+
| No log | 6.5135 | 482 | 0.7720 | 0.5295 | 0.7720 | 0.8786 |
|
| 293 |
+
| No log | 6.5405 | 484 | 0.7371 | 0.4611 | 0.7371 | 0.8585 |
|
| 294 |
+
| No log | 6.5676 | 486 | 0.7082 | 0.5849 | 0.7082 | 0.8415 |
|
| 295 |
+
| No log | 6.5946 | 488 | 0.7257 | 0.5766 | 0.7257 | 0.8519 |
|
| 296 |
+
| No log | 6.6216 | 490 | 0.7340 | 0.5247 | 0.7340 | 0.8568 |
|
| 297 |
+
| No log | 6.6486 | 492 | 0.7130 | 0.5318 | 0.7130 | 0.8444 |
|
| 298 |
+
| No log | 6.6757 | 494 | 0.6983 | 0.6321 | 0.6983 | 0.8356 |
|
| 299 |
+
| No log | 6.7027 | 496 | 0.6878 | 0.6840 | 0.6878 | 0.8294 |
|
| 300 |
+
| No log | 6.7297 | 498 | 0.7189 | 0.6691 | 0.7189 | 0.8479 |
|
| 301 |
+
| 0.3657 | 6.7568 | 500 | 0.7898 | 0.5818 | 0.7898 | 0.8887 |
|
| 302 |
+
| 0.3657 | 6.7838 | 502 | 0.8013 | 0.5637 | 0.8013 | 0.8951 |
|
| 303 |
+
| 0.3657 | 6.8108 | 504 | 0.7740 | 0.5934 | 0.7740 | 0.8798 |
|
| 304 |
+
| 0.3657 | 6.8378 | 506 | 0.7761 | 0.5881 | 0.7761 | 0.8810 |
|
| 305 |
+
| 0.3657 | 6.8649 | 508 | 0.7499 | 0.5569 | 0.7499 | 0.8659 |
|
| 306 |
+
| 0.3657 | 6.8919 | 510 | 0.7424 | 0.4571 | 0.7424 | 0.8616 |
|
| 307 |
+
| 0.3657 | 6.9189 | 512 | 0.7499 | 0.4571 | 0.7499 | 0.8660 |
|
| 308 |
+
| 0.3657 | 6.9459 | 514 | 0.7757 | 0.5663 | 0.7757 | 0.8807 |
|
| 309 |
+
| 0.3657 | 6.9730 | 516 | 0.8716 | 0.5029 | 0.8716 | 0.9336 |
|
| 310 |
+
|
| 311 |
+
|
| 312 |
+
### Framework versions
|
| 313 |
+
|
| 314 |
+
- Transformers 4.44.2
|
| 315 |
+
- Pytorch 2.4.0+cu118
|
| 316 |
+
- Datasets 2.21.0
|
| 317 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 64000
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4afe7f14bccd81f4ba5f6a6a725a5e8102423ee9cb0e621e70460e56de47474
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebd678b1a7ec7b6983fcf5b55650145fa0b4d0cd1a157a0b7c742fba90e0fc47
|
| 3 |
+
size 5304
|