Training in progress, step 500
Browse files- README.md +332 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k15_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_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k15_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: 0.5753
|
| 19 |
+
- Qwk: 0.4420
|
| 20 |
+
- Mse: 0.5753
|
| 21 |
+
- Rmse: 0.7585
|
| 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 | 0.0263 | 2 | 2.4414 | -0.0788 | 2.4414 | 1.5625 |
|
| 53 |
+
| No log | 0.0526 | 4 | 1.2078 | -0.0291 | 1.2078 | 1.0990 |
|
| 54 |
+
| No log | 0.0789 | 6 | 0.9122 | 0.0423 | 0.9122 | 0.9551 |
|
| 55 |
+
| No log | 0.1053 | 8 | 0.7719 | 0.2204 | 0.7719 | 0.8786 |
|
| 56 |
+
| No log | 0.1316 | 10 | 0.9180 | 0.2164 | 0.9180 | 0.9581 |
|
| 57 |
+
| No log | 0.1579 | 12 | 0.7960 | 0.2193 | 0.7960 | 0.8922 |
|
| 58 |
+
| No log | 0.1842 | 14 | 0.6839 | 0.3636 | 0.6839 | 0.8270 |
|
| 59 |
+
| No log | 0.2105 | 16 | 1.2041 | 0.0511 | 1.2041 | 1.0973 |
|
| 60 |
+
| No log | 0.2368 | 18 | 1.3821 | 0.0560 | 1.3821 | 1.1756 |
|
| 61 |
+
| No log | 0.2632 | 20 | 1.0322 | 0.1973 | 1.0322 | 1.0160 |
|
| 62 |
+
| No log | 0.2895 | 22 | 0.7032 | 0.3610 | 0.7032 | 0.8386 |
|
| 63 |
+
| No log | 0.3158 | 24 | 0.7085 | 0.4036 | 0.7085 | 0.8417 |
|
| 64 |
+
| No log | 0.3421 | 26 | 0.8110 | 0.3502 | 0.8110 | 0.9005 |
|
| 65 |
+
| No log | 0.3684 | 28 | 0.8978 | 0.2948 | 0.8978 | 0.9475 |
|
| 66 |
+
| No log | 0.3947 | 30 | 0.9813 | 0.2437 | 0.9813 | 0.9906 |
|
| 67 |
+
| No log | 0.4211 | 32 | 0.8810 | 0.2408 | 0.8810 | 0.9386 |
|
| 68 |
+
| No log | 0.4474 | 34 | 0.7024 | 0.1744 | 0.7024 | 0.8381 |
|
| 69 |
+
| No log | 0.4737 | 36 | 0.6873 | 0.0327 | 0.6873 | 0.8291 |
|
| 70 |
+
| No log | 0.5 | 38 | 0.7577 | 0.1327 | 0.7577 | 0.8704 |
|
| 71 |
+
| No log | 0.5263 | 40 | 0.8740 | 0.1339 | 0.8740 | 0.9349 |
|
| 72 |
+
| No log | 0.5526 | 42 | 1.0026 | 0.1609 | 1.0026 | 1.0013 |
|
| 73 |
+
| No log | 0.5789 | 44 | 1.0856 | 0.1549 | 1.0856 | 1.0419 |
|
| 74 |
+
| No log | 0.6053 | 46 | 1.0881 | 0.0983 | 1.0881 | 1.0431 |
|
| 75 |
+
| No log | 0.6316 | 48 | 0.9599 | 0.1697 | 0.9599 | 0.9797 |
|
| 76 |
+
| No log | 0.6579 | 50 | 0.7947 | 0.0937 | 0.7947 | 0.8915 |
|
| 77 |
+
| No log | 0.6842 | 52 | 0.7525 | 0.0 | 0.7525 | 0.8675 |
|
| 78 |
+
| No log | 0.7105 | 54 | 0.7247 | 0.0428 | 0.7247 | 0.8513 |
|
| 79 |
+
| No log | 0.7368 | 56 | 0.6935 | 0.1287 | 0.6935 | 0.8328 |
|
| 80 |
+
| No log | 0.7632 | 58 | 0.7085 | 0.2103 | 0.7085 | 0.8417 |
|
| 81 |
+
| No log | 0.7895 | 60 | 0.7825 | 0.1339 | 0.7825 | 0.8846 |
|
| 82 |
+
| No log | 0.8158 | 62 | 0.9562 | 0.2813 | 0.9562 | 0.9779 |
|
| 83 |
+
| No log | 0.8421 | 64 | 1.0400 | 0.1786 | 1.0400 | 1.0198 |
|
| 84 |
+
| No log | 0.8684 | 66 | 0.8977 | 0.3442 | 0.8977 | 0.9475 |
|
| 85 |
+
| No log | 0.8947 | 68 | 0.8782 | 0.2817 | 0.8782 | 0.9371 |
|
| 86 |
+
| No log | 0.9211 | 70 | 0.9170 | 0.2411 | 0.9170 | 0.9576 |
|
| 87 |
+
| No log | 0.9474 | 72 | 0.8400 | 0.2583 | 0.8400 | 0.9165 |
|
| 88 |
+
| No log | 0.9737 | 74 | 0.8426 | 0.1605 | 0.8426 | 0.9179 |
|
| 89 |
+
| No log | 1.0 | 76 | 0.9978 | 0.2437 | 0.9978 | 0.9989 |
|
| 90 |
+
| No log | 1.0263 | 78 | 1.0015 | 0.1882 | 1.0015 | 1.0007 |
|
| 91 |
+
| No log | 1.0526 | 80 | 0.8298 | 0.1358 | 0.8298 | 0.9109 |
|
| 92 |
+
| No log | 1.0789 | 82 | 0.6340 | 0.2405 | 0.6340 | 0.7962 |
|
| 93 |
+
| No log | 1.1053 | 84 | 0.7099 | 0.3372 | 0.7099 | 0.8425 |
|
| 94 |
+
| No log | 1.1316 | 86 | 0.7165 | 0.3637 | 0.7165 | 0.8464 |
|
| 95 |
+
| No log | 1.1579 | 88 | 0.6199 | 0.2787 | 0.6199 | 0.7873 |
|
| 96 |
+
| No log | 1.1842 | 90 | 0.7220 | 0.2817 | 0.7220 | 0.8497 |
|
| 97 |
+
| No log | 1.2105 | 92 | 0.9949 | 0.1253 | 0.9949 | 0.9975 |
|
| 98 |
+
| No log | 1.2368 | 94 | 1.0359 | 0.1727 | 1.0359 | 1.0178 |
|
| 99 |
+
| No log | 1.2632 | 96 | 0.9030 | 0.2070 | 0.9030 | 0.9502 |
|
| 100 |
+
| No log | 1.2895 | 98 | 0.6584 | 0.3399 | 0.6584 | 0.8114 |
|
| 101 |
+
| No log | 1.3158 | 100 | 0.6041 | 0.3352 | 0.6041 | 0.7772 |
|
| 102 |
+
| No log | 1.3421 | 102 | 0.6303 | 0.2994 | 0.6303 | 0.7939 |
|
| 103 |
+
| No log | 1.3684 | 104 | 0.8002 | 0.3459 | 0.8002 | 0.8945 |
|
| 104 |
+
| No log | 1.3947 | 106 | 0.9982 | 0.3173 | 0.9982 | 0.9991 |
|
| 105 |
+
| No log | 1.4211 | 108 | 0.9828 | 0.2928 | 0.9828 | 0.9914 |
|
| 106 |
+
| No log | 1.4474 | 110 | 0.8470 | 0.3230 | 0.8470 | 0.9203 |
|
| 107 |
+
| No log | 1.4737 | 112 | 0.7621 | 0.3302 | 0.7621 | 0.8730 |
|
| 108 |
+
| No log | 1.5 | 114 | 0.7995 | 0.3754 | 0.7995 | 0.8942 |
|
| 109 |
+
| No log | 1.5263 | 116 | 0.8308 | 0.3376 | 0.8308 | 0.9115 |
|
| 110 |
+
| No log | 1.5526 | 118 | 0.8777 | 0.3401 | 0.8777 | 0.9369 |
|
| 111 |
+
| No log | 1.5789 | 120 | 0.9128 | 0.3643 | 0.9128 | 0.9554 |
|
| 112 |
+
| No log | 1.6053 | 122 | 0.8142 | 0.3851 | 0.8142 | 0.9024 |
|
| 113 |
+
| No log | 1.6316 | 124 | 0.7069 | 0.2652 | 0.7069 | 0.8408 |
|
| 114 |
+
| No log | 1.6579 | 126 | 0.6913 | 0.2023 | 0.6913 | 0.8314 |
|
| 115 |
+
| No log | 1.6842 | 128 | 0.6860 | 0.2590 | 0.6860 | 0.8283 |
|
| 116 |
+
| No log | 1.7105 | 130 | 0.6884 | 0.2590 | 0.6884 | 0.8297 |
|
| 117 |
+
| No log | 1.7368 | 132 | 0.7003 | 0.2509 | 0.7003 | 0.8368 |
|
| 118 |
+
| No log | 1.7632 | 134 | 0.7005 | 0.3111 | 0.7005 | 0.8370 |
|
| 119 |
+
| No log | 1.7895 | 136 | 0.7178 | 0.3296 | 0.7178 | 0.8473 |
|
| 120 |
+
| No log | 1.8158 | 138 | 0.7210 | 0.2877 | 0.7210 | 0.8491 |
|
| 121 |
+
| No log | 1.8421 | 140 | 0.7171 | 0.3478 | 0.7171 | 0.8468 |
|
| 122 |
+
| No log | 1.8684 | 142 | 0.7185 | 0.3738 | 0.7185 | 0.8476 |
|
| 123 |
+
| No log | 1.8947 | 144 | 0.7142 | 0.4343 | 0.7142 | 0.8451 |
|
| 124 |
+
| No log | 1.9211 | 146 | 0.6952 | 0.4051 | 0.6952 | 0.8338 |
|
| 125 |
+
| No log | 1.9474 | 148 | 0.6816 | 0.3648 | 0.6816 | 0.8256 |
|
| 126 |
+
| No log | 1.9737 | 150 | 0.7445 | 0.3203 | 0.7445 | 0.8629 |
|
| 127 |
+
| No log | 2.0 | 152 | 0.7352 | 0.3706 | 0.7352 | 0.8575 |
|
| 128 |
+
| No log | 2.0263 | 154 | 0.6682 | 0.3999 | 0.6682 | 0.8174 |
|
| 129 |
+
| No log | 2.0526 | 156 | 0.5680 | 0.4928 | 0.5680 | 0.7537 |
|
| 130 |
+
| No log | 2.0789 | 158 | 0.5321 | 0.5516 | 0.5321 | 0.7294 |
|
| 131 |
+
| No log | 2.1053 | 160 | 0.5225 | 0.5017 | 0.5225 | 0.7228 |
|
| 132 |
+
| No log | 2.1316 | 162 | 0.5117 | 0.5208 | 0.5117 | 0.7154 |
|
| 133 |
+
| No log | 2.1579 | 164 | 0.6057 | 0.4341 | 0.6057 | 0.7782 |
|
| 134 |
+
| No log | 2.1842 | 166 | 0.6180 | 0.4395 | 0.6180 | 0.7861 |
|
| 135 |
+
| No log | 2.2105 | 168 | 0.5341 | 0.4838 | 0.5341 | 0.7309 |
|
| 136 |
+
| No log | 2.2368 | 170 | 0.4893 | 0.5151 | 0.4893 | 0.6995 |
|
| 137 |
+
| No log | 2.2632 | 172 | 0.4821 | 0.5567 | 0.4821 | 0.6943 |
|
| 138 |
+
| No log | 2.2895 | 174 | 0.4882 | 0.6339 | 0.4882 | 0.6987 |
|
| 139 |
+
| No log | 2.3158 | 176 | 0.5400 | 0.5687 | 0.5400 | 0.7349 |
|
| 140 |
+
| No log | 2.3421 | 178 | 0.5819 | 0.5327 | 0.5819 | 0.7628 |
|
| 141 |
+
| No log | 2.3684 | 180 | 0.5584 | 0.5822 | 0.5584 | 0.7473 |
|
| 142 |
+
| No log | 2.3947 | 182 | 0.5540 | 0.5628 | 0.5540 | 0.7443 |
|
| 143 |
+
| No log | 2.4211 | 184 | 0.5460 | 0.5798 | 0.5460 | 0.7389 |
|
| 144 |
+
| No log | 2.4474 | 186 | 0.5607 | 0.6158 | 0.5607 | 0.7488 |
|
| 145 |
+
| No log | 2.4737 | 188 | 0.5904 | 0.4883 | 0.5904 | 0.7684 |
|
| 146 |
+
| No log | 2.5 | 190 | 0.6468 | 0.4843 | 0.6468 | 0.8042 |
|
| 147 |
+
| No log | 2.5263 | 192 | 0.7956 | 0.4200 | 0.7956 | 0.8920 |
|
| 148 |
+
| No log | 2.5526 | 194 | 0.7980 | 0.3998 | 0.7980 | 0.8933 |
|
| 149 |
+
| No log | 2.5789 | 196 | 0.7533 | 0.3998 | 0.7533 | 0.8679 |
|
| 150 |
+
| No log | 2.6053 | 198 | 0.6736 | 0.4805 | 0.6736 | 0.8207 |
|
| 151 |
+
| No log | 2.6316 | 200 | 0.6159 | 0.5656 | 0.6159 | 0.7848 |
|
| 152 |
+
| No log | 2.6579 | 202 | 0.5675 | 0.5070 | 0.5675 | 0.7533 |
|
| 153 |
+
| No log | 2.6842 | 204 | 0.5698 | 0.5784 | 0.5698 | 0.7549 |
|
| 154 |
+
| No log | 2.7105 | 206 | 0.5483 | 0.5711 | 0.5483 | 0.7405 |
|
| 155 |
+
| No log | 2.7368 | 208 | 0.5479 | 0.6247 | 0.5479 | 0.7402 |
|
| 156 |
+
| No log | 2.7632 | 210 | 0.6116 | 0.5041 | 0.6116 | 0.7820 |
|
| 157 |
+
| No log | 2.7895 | 212 | 0.8147 | 0.3735 | 0.8147 | 0.9026 |
|
| 158 |
+
| No log | 2.8158 | 214 | 0.8412 | 0.4033 | 0.8412 | 0.9172 |
|
| 159 |
+
| No log | 2.8421 | 216 | 0.6685 | 0.4472 | 0.6685 | 0.8176 |
|
| 160 |
+
| No log | 2.8684 | 218 | 0.5515 | 0.6362 | 0.5515 | 0.7426 |
|
| 161 |
+
| No log | 2.8947 | 220 | 0.5789 | 0.6199 | 0.5789 | 0.7608 |
|
| 162 |
+
| No log | 2.9211 | 222 | 0.6133 | 0.6282 | 0.6133 | 0.7831 |
|
| 163 |
+
| No log | 2.9474 | 224 | 0.5794 | 0.6127 | 0.5794 | 0.7612 |
|
| 164 |
+
| No log | 2.9737 | 226 | 0.5712 | 0.5929 | 0.5712 | 0.7558 |
|
| 165 |
+
| No log | 3.0 | 228 | 0.6663 | 0.4753 | 0.6663 | 0.8163 |
|
| 166 |
+
| No log | 3.0263 | 230 | 0.6230 | 0.4486 | 0.6230 | 0.7893 |
|
| 167 |
+
| No log | 3.0526 | 232 | 0.5676 | 0.5457 | 0.5676 | 0.7534 |
|
| 168 |
+
| No log | 3.0789 | 234 | 0.5400 | 0.5974 | 0.5400 | 0.7349 |
|
| 169 |
+
| No log | 3.1053 | 236 | 0.5838 | 0.5485 | 0.5838 | 0.7641 |
|
| 170 |
+
| No log | 3.1316 | 238 | 0.5328 | 0.5845 | 0.5328 | 0.7300 |
|
| 171 |
+
| No log | 3.1579 | 240 | 0.5473 | 0.5919 | 0.5473 | 0.7398 |
|
| 172 |
+
| No log | 3.1842 | 242 | 0.6999 | 0.4396 | 0.6999 | 0.8366 |
|
| 173 |
+
| No log | 3.2105 | 244 | 0.7318 | 0.4260 | 0.7318 | 0.8554 |
|
| 174 |
+
| No log | 3.2368 | 246 | 0.6074 | 0.4987 | 0.6074 | 0.7793 |
|
| 175 |
+
| No log | 3.2632 | 248 | 0.5199 | 0.5781 | 0.5199 | 0.7210 |
|
| 176 |
+
| No log | 3.2895 | 250 | 0.5225 | 0.5494 | 0.5225 | 0.7229 |
|
| 177 |
+
| No log | 3.3158 | 252 | 0.5569 | 0.5919 | 0.5569 | 0.7463 |
|
| 178 |
+
| No log | 3.3421 | 254 | 0.6944 | 0.5098 | 0.6944 | 0.8333 |
|
| 179 |
+
| No log | 3.3684 | 256 | 0.7556 | 0.4413 | 0.7556 | 0.8693 |
|
| 180 |
+
| No log | 3.3947 | 258 | 0.6350 | 0.4987 | 0.6350 | 0.7969 |
|
| 181 |
+
| No log | 3.4211 | 260 | 0.5091 | 0.5941 | 0.5091 | 0.7135 |
|
| 182 |
+
| No log | 3.4474 | 262 | 0.5151 | 0.5195 | 0.5151 | 0.7177 |
|
| 183 |
+
| No log | 3.4737 | 264 | 0.5456 | 0.4479 | 0.5456 | 0.7387 |
|
| 184 |
+
| No log | 3.5 | 266 | 0.5391 | 0.4479 | 0.5391 | 0.7342 |
|
| 185 |
+
| No log | 3.5263 | 268 | 0.5207 | 0.5095 | 0.5207 | 0.7216 |
|
| 186 |
+
| No log | 3.5526 | 270 | 0.5671 | 0.4370 | 0.5671 | 0.7531 |
|
| 187 |
+
| No log | 3.5789 | 272 | 0.6087 | 0.4825 | 0.6087 | 0.7802 |
|
| 188 |
+
| No log | 3.6053 | 274 | 0.5636 | 0.4813 | 0.5636 | 0.7507 |
|
| 189 |
+
| No log | 3.6316 | 276 | 0.5270 | 0.4904 | 0.5270 | 0.7259 |
|
| 190 |
+
| No log | 3.6579 | 278 | 0.5333 | 0.5252 | 0.5333 | 0.7303 |
|
| 191 |
+
| No log | 3.6842 | 280 | 0.5694 | 0.5268 | 0.5694 | 0.7546 |
|
| 192 |
+
| No log | 3.7105 | 282 | 0.6479 | 0.4930 | 0.6479 | 0.8049 |
|
| 193 |
+
| No log | 3.7368 | 284 | 0.7784 | 0.3786 | 0.7784 | 0.8823 |
|
| 194 |
+
| No log | 3.7632 | 286 | 0.7229 | 0.3638 | 0.7229 | 0.8502 |
|
| 195 |
+
| No log | 3.7895 | 288 | 0.5634 | 0.5702 | 0.5634 | 0.7506 |
|
| 196 |
+
| No log | 3.8158 | 290 | 0.5330 | 0.4397 | 0.5330 | 0.7301 |
|
| 197 |
+
| No log | 3.8421 | 292 | 0.6024 | 0.3972 | 0.6024 | 0.7762 |
|
| 198 |
+
| No log | 3.8684 | 294 | 0.5802 | 0.4663 | 0.5802 | 0.7617 |
|
| 199 |
+
| No log | 3.8947 | 296 | 0.5382 | 0.4639 | 0.5382 | 0.7336 |
|
| 200 |
+
| No log | 3.9211 | 298 | 0.5324 | 0.5580 | 0.5324 | 0.7296 |
|
| 201 |
+
| No log | 3.9474 | 300 | 0.5974 | 0.5217 | 0.5974 | 0.7729 |
|
| 202 |
+
| No log | 3.9737 | 302 | 0.6146 | 0.4652 | 0.6146 | 0.7840 |
|
| 203 |
+
| No log | 4.0 | 304 | 0.5610 | 0.5390 | 0.5610 | 0.7490 |
|
| 204 |
+
| No log | 4.0263 | 306 | 0.5568 | 0.4828 | 0.5568 | 0.7462 |
|
| 205 |
+
| No log | 4.0526 | 308 | 0.6995 | 0.3494 | 0.6995 | 0.8364 |
|
| 206 |
+
| No log | 4.0789 | 310 | 0.8543 | 0.3938 | 0.8543 | 0.9243 |
|
| 207 |
+
| No log | 4.1053 | 312 | 0.7987 | 0.3709 | 0.7987 | 0.8937 |
|
| 208 |
+
| No log | 4.1316 | 314 | 0.6497 | 0.4112 | 0.6497 | 0.8060 |
|
| 209 |
+
| No log | 4.1579 | 316 | 0.5835 | 0.5589 | 0.5835 | 0.7639 |
|
| 210 |
+
| No log | 4.1842 | 318 | 0.6019 | 0.5669 | 0.6019 | 0.7759 |
|
| 211 |
+
| No log | 4.2105 | 320 | 0.6131 | 0.56 | 0.6131 | 0.7830 |
|
| 212 |
+
| No log | 4.2368 | 322 | 0.6397 | 0.5683 | 0.6397 | 0.7998 |
|
| 213 |
+
| No log | 4.2632 | 324 | 0.6548 | 0.5039 | 0.6548 | 0.8092 |
|
| 214 |
+
| No log | 4.2895 | 326 | 0.6479 | 0.5406 | 0.6479 | 0.8049 |
|
| 215 |
+
| No log | 4.3158 | 328 | 0.6369 | 0.5519 | 0.6369 | 0.7980 |
|
| 216 |
+
| No log | 4.3421 | 330 | 0.6305 | 0.5318 | 0.6305 | 0.7940 |
|
| 217 |
+
| No log | 4.3684 | 332 | 0.6388 | 0.5164 | 0.6388 | 0.7992 |
|
| 218 |
+
| No log | 4.3947 | 334 | 0.6145 | 0.4966 | 0.6145 | 0.7839 |
|
| 219 |
+
| No log | 4.4211 | 336 | 0.5803 | 0.5492 | 0.5803 | 0.7618 |
|
| 220 |
+
| No log | 4.4474 | 338 | 0.6195 | 0.4914 | 0.6195 | 0.7871 |
|
| 221 |
+
| No log | 4.4737 | 340 | 0.6297 | 0.4859 | 0.6297 | 0.7936 |
|
| 222 |
+
| No log | 4.5 | 342 | 0.5802 | 0.4832 | 0.5802 | 0.7617 |
|
| 223 |
+
| No log | 4.5263 | 344 | 0.5464 | 0.4747 | 0.5464 | 0.7392 |
|
| 224 |
+
| No log | 4.5526 | 346 | 0.6084 | 0.4052 | 0.6084 | 0.7800 |
|
| 225 |
+
| No log | 4.5789 | 348 | 0.6263 | 0.3637 | 0.6263 | 0.7914 |
|
| 226 |
+
| No log | 4.6053 | 350 | 0.5743 | 0.5195 | 0.5743 | 0.7579 |
|
| 227 |
+
| No log | 4.6316 | 352 | 0.5536 | 0.5340 | 0.5536 | 0.7440 |
|
| 228 |
+
| No log | 4.6579 | 354 | 0.5633 | 0.5168 | 0.5633 | 0.7506 |
|
| 229 |
+
| No log | 4.6842 | 356 | 0.6186 | 0.4636 | 0.6186 | 0.7865 |
|
| 230 |
+
| No log | 4.7105 | 358 | 0.6397 | 0.4545 | 0.6397 | 0.7998 |
|
| 231 |
+
| No log | 4.7368 | 360 | 0.5908 | 0.4935 | 0.5908 | 0.7686 |
|
| 232 |
+
| No log | 4.7632 | 362 | 0.5534 | 0.5114 | 0.5534 | 0.7439 |
|
| 233 |
+
| No log | 4.7895 | 364 | 0.5626 | 0.5627 | 0.5626 | 0.7501 |
|
| 234 |
+
| No log | 4.8158 | 366 | 0.6331 | 0.4723 | 0.6331 | 0.7957 |
|
| 235 |
+
| No log | 4.8421 | 368 | 0.6435 | 0.4859 | 0.6435 | 0.8022 |
|
| 236 |
+
| No log | 4.8684 | 370 | 0.5692 | 0.4997 | 0.5692 | 0.7544 |
|
| 237 |
+
| No log | 4.8947 | 372 | 0.5482 | 0.5656 | 0.5482 | 0.7404 |
|
| 238 |
+
| No log | 4.9211 | 374 | 0.5462 | 0.5533 | 0.5462 | 0.7390 |
|
| 239 |
+
| No log | 4.9474 | 376 | 0.5580 | 0.4824 | 0.5580 | 0.7470 |
|
| 240 |
+
| No log | 4.9737 | 378 | 0.6174 | 0.5101 | 0.6174 | 0.7858 |
|
| 241 |
+
| No log | 5.0 | 380 | 0.6278 | 0.5696 | 0.6278 | 0.7923 |
|
| 242 |
+
| No log | 5.0263 | 382 | 0.5639 | 0.4980 | 0.5639 | 0.7509 |
|
| 243 |
+
| No log | 5.0526 | 384 | 0.5246 | 0.4839 | 0.5246 | 0.7243 |
|
| 244 |
+
| No log | 5.0789 | 386 | 0.5058 | 0.5095 | 0.5058 | 0.7112 |
|
| 245 |
+
| No log | 5.1053 | 388 | 0.5090 | 0.5715 | 0.5090 | 0.7135 |
|
| 246 |
+
| No log | 5.1316 | 390 | 0.5079 | 0.5614 | 0.5079 | 0.7126 |
|
| 247 |
+
| No log | 5.1579 | 392 | 0.4980 | 0.5797 | 0.4980 | 0.7057 |
|
| 248 |
+
| No log | 5.1842 | 394 | 0.6004 | 0.5297 | 0.6004 | 0.7749 |
|
| 249 |
+
| No log | 5.2105 | 396 | 0.6963 | 0.4488 | 0.6963 | 0.8344 |
|
| 250 |
+
| No log | 5.2368 | 398 | 0.6895 | 0.4668 | 0.6895 | 0.8303 |
|
| 251 |
+
| No log | 5.2632 | 400 | 0.5630 | 0.5283 | 0.5630 | 0.7503 |
|
| 252 |
+
| No log | 5.2895 | 402 | 0.4949 | 0.5580 | 0.4949 | 0.7035 |
|
| 253 |
+
| No log | 5.3158 | 404 | 0.5153 | 0.4945 | 0.5153 | 0.7178 |
|
| 254 |
+
| No log | 5.3421 | 406 | 0.5208 | 0.4753 | 0.5208 | 0.7216 |
|
| 255 |
+
| No log | 5.3684 | 408 | 0.4845 | 0.5852 | 0.4845 | 0.6961 |
|
| 256 |
+
| No log | 5.3947 | 410 | 0.4860 | 0.5993 | 0.4860 | 0.6971 |
|
| 257 |
+
| No log | 5.4211 | 412 | 0.5586 | 0.5932 | 0.5586 | 0.7474 |
|
| 258 |
+
| No log | 5.4474 | 414 | 0.5925 | 0.4972 | 0.5925 | 0.7697 |
|
| 259 |
+
| No log | 5.4737 | 416 | 0.5613 | 0.5848 | 0.5613 | 0.7492 |
|
| 260 |
+
| No log | 5.5 | 418 | 0.5479 | 0.6247 | 0.5479 | 0.7402 |
|
| 261 |
+
| No log | 5.5263 | 420 | 0.5404 | 0.5523 | 0.5404 | 0.7351 |
|
| 262 |
+
| No log | 5.5526 | 422 | 0.5438 | 0.5061 | 0.5438 | 0.7374 |
|
| 263 |
+
| No log | 5.5789 | 424 | 0.5548 | 0.4322 | 0.5548 | 0.7449 |
|
| 264 |
+
| No log | 5.6053 | 426 | 0.5550 | 0.3863 | 0.5550 | 0.7450 |
|
| 265 |
+
| No log | 5.6316 | 428 | 0.5627 | 0.3808 | 0.5627 | 0.7501 |
|
| 266 |
+
| No log | 5.6579 | 430 | 0.5957 | 0.4307 | 0.5957 | 0.7718 |
|
| 267 |
+
| No log | 5.6842 | 432 | 0.6687 | 0.3849 | 0.6687 | 0.8178 |
|
| 268 |
+
| No log | 5.7105 | 434 | 0.7544 | 0.3119 | 0.7544 | 0.8686 |
|
| 269 |
+
| No log | 5.7368 | 436 | 0.7038 | 0.3499 | 0.7038 | 0.8389 |
|
| 270 |
+
| No log | 5.7632 | 438 | 0.5619 | 0.5127 | 0.5619 | 0.7496 |
|
| 271 |
+
| No log | 5.7895 | 440 | 0.5286 | 0.6267 | 0.5286 | 0.7271 |
|
| 272 |
+
| No log | 5.8158 | 442 | 0.5313 | 0.6267 | 0.5313 | 0.7289 |
|
| 273 |
+
| No log | 5.8421 | 444 | 0.5522 | 0.5710 | 0.5522 | 0.7431 |
|
| 274 |
+
| No log | 5.8684 | 446 | 0.5357 | 0.5781 | 0.5357 | 0.7319 |
|
| 275 |
+
| No log | 5.8947 | 448 | 0.5203 | 0.5565 | 0.5203 | 0.7213 |
|
| 276 |
+
| No log | 5.9211 | 450 | 0.5164 | 0.5565 | 0.5164 | 0.7186 |
|
| 277 |
+
| No log | 5.9474 | 452 | 0.5300 | 0.5797 | 0.5300 | 0.7280 |
|
| 278 |
+
| No log | 5.9737 | 454 | 0.5234 | 0.5357 | 0.5234 | 0.7234 |
|
| 279 |
+
| No log | 6.0 | 456 | 0.5185 | 0.5413 | 0.5185 | 0.7201 |
|
| 280 |
+
| No log | 6.0263 | 458 | 0.5212 | 0.5195 | 0.5212 | 0.7220 |
|
| 281 |
+
| No log | 6.0526 | 460 | 0.5303 | 0.5213 | 0.5303 | 0.7282 |
|
| 282 |
+
| No log | 6.0789 | 462 | 0.5440 | 0.5463 | 0.5440 | 0.7376 |
|
| 283 |
+
| No log | 6.1053 | 464 | 0.5369 | 0.5061 | 0.5369 | 0.7327 |
|
| 284 |
+
| No log | 6.1316 | 466 | 0.5756 | 0.4674 | 0.5756 | 0.7587 |
|
| 285 |
+
| No log | 6.1579 | 468 | 0.5816 | 0.4674 | 0.5816 | 0.7627 |
|
| 286 |
+
| No log | 6.1842 | 470 | 0.5404 | 0.5195 | 0.5404 | 0.7351 |
|
| 287 |
+
| No log | 6.2105 | 472 | 0.5336 | 0.4953 | 0.5336 | 0.7305 |
|
| 288 |
+
| No log | 6.2368 | 474 | 0.5509 | 0.5522 | 0.5509 | 0.7422 |
|
| 289 |
+
| No log | 6.2632 | 476 | 0.6054 | 0.4789 | 0.6054 | 0.7781 |
|
| 290 |
+
| No log | 6.2895 | 478 | 0.5822 | 0.4674 | 0.5822 | 0.7630 |
|
| 291 |
+
| No log | 6.3158 | 480 | 0.5485 | 0.5319 | 0.5485 | 0.7406 |
|
| 292 |
+
| No log | 6.3421 | 482 | 0.5312 | 0.5430 | 0.5312 | 0.7289 |
|
| 293 |
+
| No log | 6.3684 | 484 | 0.5257 | 0.5304 | 0.5257 | 0.7250 |
|
| 294 |
+
| No log | 6.3947 | 486 | 0.5430 | 0.4611 | 0.5430 | 0.7369 |
|
| 295 |
+
| No log | 6.4211 | 488 | 0.5617 | 0.4283 | 0.5617 | 0.7495 |
|
| 296 |
+
| No log | 6.4474 | 490 | 0.5606 | 0.3745 | 0.5606 | 0.7487 |
|
| 297 |
+
| No log | 6.4737 | 492 | 0.5351 | 0.4173 | 0.5351 | 0.7315 |
|
| 298 |
+
| No log | 6.5 | 494 | 0.5343 | 0.3546 | 0.5343 | 0.7310 |
|
| 299 |
+
| No log | 6.5263 | 496 | 0.5293 | 0.4052 | 0.5293 | 0.7276 |
|
| 300 |
+
| No log | 6.5526 | 498 | 0.5344 | 0.4970 | 0.5344 | 0.7310 |
|
| 301 |
+
| 0.327 | 6.5789 | 500 | 0.5187 | 0.4742 | 0.5187 | 0.7202 |
|
| 302 |
+
| 0.327 | 6.6053 | 502 | 0.5047 | 0.4885 | 0.5047 | 0.7105 |
|
| 303 |
+
| 0.327 | 6.6316 | 504 | 0.5028 | 0.6060 | 0.5028 | 0.7091 |
|
| 304 |
+
| 0.327 | 6.6579 | 506 | 0.5059 | 0.6254 | 0.5059 | 0.7113 |
|
| 305 |
+
| 0.327 | 6.6842 | 508 | 0.5210 | 0.5662 | 0.5210 | 0.7218 |
|
| 306 |
+
| 0.327 | 6.7105 | 510 | 0.5178 | 0.6171 | 0.5178 | 0.7196 |
|
| 307 |
+
| 0.327 | 6.7368 | 512 | 0.5129 | 0.6171 | 0.5129 | 0.7162 |
|
| 308 |
+
| 0.327 | 6.7632 | 514 | 0.5113 | 0.5965 | 0.5113 | 0.7151 |
|
| 309 |
+
| 0.327 | 6.7895 | 516 | 0.5103 | 0.5782 | 0.5103 | 0.7143 |
|
| 310 |
+
| 0.327 | 6.8158 | 518 | 0.5191 | 0.5985 | 0.5191 | 0.7205 |
|
| 311 |
+
| 0.327 | 6.8421 | 520 | 0.5504 | 0.5642 | 0.5504 | 0.7419 |
|
| 312 |
+
| 0.327 | 6.8684 | 522 | 0.6154 | 0.5313 | 0.6154 | 0.7845 |
|
| 313 |
+
| 0.327 | 6.8947 | 524 | 0.7053 | 0.3290 | 0.7053 | 0.8398 |
|
| 314 |
+
| 0.327 | 6.9211 | 526 | 0.7091 | 0.3074 | 0.7091 | 0.8421 |
|
| 315 |
+
| 0.327 | 6.9474 | 528 | 0.6872 | 0.3849 | 0.6872 | 0.8290 |
|
| 316 |
+
| 0.327 | 6.9737 | 530 | 0.5927 | 0.4770 | 0.5927 | 0.7699 |
|
| 317 |
+
| 0.327 | 7.0 | 532 | 0.5569 | 0.5422 | 0.5569 | 0.7462 |
|
| 318 |
+
| 0.327 | 7.0263 | 534 | 0.5605 | 0.5232 | 0.5605 | 0.7487 |
|
| 319 |
+
| 0.327 | 7.0526 | 536 | 0.5947 | 0.5152 | 0.5947 | 0.7711 |
|
| 320 |
+
| 0.327 | 7.0789 | 538 | 0.6888 | 0.3633 | 0.6888 | 0.8300 |
|
| 321 |
+
| 0.327 | 7.1053 | 540 | 0.6756 | 0.3387 | 0.6756 | 0.8220 |
|
| 322 |
+
| 0.327 | 7.1316 | 542 | 0.5957 | 0.4161 | 0.5957 | 0.7718 |
|
| 323 |
+
| 0.327 | 7.1579 | 544 | 0.5683 | 0.4354 | 0.5683 | 0.7538 |
|
| 324 |
+
| 0.327 | 7.1842 | 546 | 0.5753 | 0.4420 | 0.5753 | 0.7585 |
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
### Framework versions
|
| 328 |
+
|
| 329 |
+
- Transformers 4.44.2
|
| 330 |
+
- Pytorch 2.4.0+cu118
|
| 331 |
+
- Datasets 2.21.0
|
| 332 |
+
- 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 sha256:425f0363da257fb4e9eff3be7abf2f9e2c6f4b70cbc09504dcd11994dd8ab2dd
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f03248aa69300b8efc298e4f40414d81d80dc3451eb76a1bb8a2146e67bb3b82
|
| 3 |
+
size 5304
|