Training in progress, step 500
Browse files- README.md +322 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_run1_AugV5_k19_task5_organization
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k19_task5_organization
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.6533
|
| 19 |
+
- Qwk: 0.5579
|
| 20 |
+
- Mse: 0.6533
|
| 21 |
+
- Rmse: 0.8082
|
| 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 | 0.0211 | 2 | 3.8878 | -0.0172 | 3.8878 | 1.9717 |
|
| 53 |
+
| No log | 0.0421 | 4 | 2.1197 | 0.1266 | 2.1197 | 1.4559 |
|
| 54 |
+
| No log | 0.0632 | 6 | 1.4797 | -0.0267 | 1.4797 | 1.2164 |
|
| 55 |
+
| No log | 0.0842 | 8 | 1.0331 | 0.2288 | 1.0331 | 1.0164 |
|
| 56 |
+
| No log | 0.1053 | 10 | 1.1162 | 0.2944 | 1.1162 | 1.0565 |
|
| 57 |
+
| No log | 0.1263 | 12 | 1.0773 | 0.2865 | 1.0773 | 1.0379 |
|
| 58 |
+
| No log | 0.1474 | 14 | 1.0048 | 0.3519 | 1.0048 | 1.0024 |
|
| 59 |
+
| No log | 0.1684 | 16 | 0.9294 | 0.3583 | 0.9294 | 0.9640 |
|
| 60 |
+
| No log | 0.1895 | 18 | 0.9248 | 0.3561 | 0.9248 | 0.9617 |
|
| 61 |
+
| No log | 0.2105 | 20 | 0.9221 | 0.3646 | 0.9221 | 0.9602 |
|
| 62 |
+
| No log | 0.2316 | 22 | 0.9957 | 0.2857 | 0.9957 | 0.9978 |
|
| 63 |
+
| No log | 0.2526 | 24 | 1.4618 | 0.2803 | 1.4618 | 1.2091 |
|
| 64 |
+
| No log | 0.2737 | 26 | 1.6526 | 0.2742 | 1.6526 | 1.2855 |
|
| 65 |
+
| No log | 0.2947 | 28 | 1.2694 | 0.2667 | 1.2694 | 1.1267 |
|
| 66 |
+
| No log | 0.3158 | 30 | 0.9206 | 0.3143 | 0.9206 | 0.9595 |
|
| 67 |
+
| No log | 0.3368 | 32 | 0.8415 | 0.3837 | 0.8415 | 0.9173 |
|
| 68 |
+
| No log | 0.3579 | 34 | 0.9117 | 0.3883 | 0.9117 | 0.9548 |
|
| 69 |
+
| No log | 0.3789 | 36 | 0.9644 | 0.3629 | 0.9644 | 0.9820 |
|
| 70 |
+
| No log | 0.4 | 38 | 0.9809 | 0.3164 | 0.9809 | 0.9904 |
|
| 71 |
+
| No log | 0.4211 | 40 | 0.9453 | 0.3308 | 0.9453 | 0.9723 |
|
| 72 |
+
| No log | 0.4421 | 42 | 0.9269 | 0.2518 | 0.9269 | 0.9627 |
|
| 73 |
+
| No log | 0.4632 | 44 | 0.9438 | 0.3625 | 0.9438 | 0.9715 |
|
| 74 |
+
| No log | 0.4842 | 46 | 0.8691 | 0.4820 | 0.8691 | 0.9322 |
|
| 75 |
+
| No log | 0.5053 | 48 | 1.0037 | 0.3431 | 1.0037 | 1.0018 |
|
| 76 |
+
| No log | 0.5263 | 50 | 1.7812 | 0.1630 | 1.7812 | 1.3346 |
|
| 77 |
+
| No log | 0.5474 | 52 | 1.9082 | 0.1593 | 1.9082 | 1.3814 |
|
| 78 |
+
| No log | 0.5684 | 54 | 1.2591 | 0.3411 | 1.2591 | 1.1221 |
|
| 79 |
+
| No log | 0.5895 | 56 | 0.8387 | 0.4828 | 0.8387 | 0.9158 |
|
| 80 |
+
| No log | 0.6105 | 58 | 0.9062 | 0.4695 | 0.9062 | 0.9519 |
|
| 81 |
+
| No log | 0.6316 | 60 | 0.9663 | 0.4578 | 0.9663 | 0.9830 |
|
| 82 |
+
| No log | 0.6526 | 62 | 0.8854 | 0.4517 | 0.8854 | 0.9409 |
|
| 83 |
+
| No log | 0.6737 | 64 | 0.8050 | 0.5523 | 0.8050 | 0.8972 |
|
| 84 |
+
| No log | 0.6947 | 66 | 0.8164 | 0.4959 | 0.8164 | 0.9035 |
|
| 85 |
+
| No log | 0.7158 | 68 | 0.9288 | 0.4233 | 0.9288 | 0.9637 |
|
| 86 |
+
| No log | 0.7368 | 70 | 0.9111 | 0.4104 | 0.9111 | 0.9545 |
|
| 87 |
+
| No log | 0.7579 | 72 | 0.7187 | 0.5961 | 0.7187 | 0.8477 |
|
| 88 |
+
| No log | 0.7789 | 74 | 0.6712 | 0.5735 | 0.6712 | 0.8193 |
|
| 89 |
+
| No log | 0.8 | 76 | 0.6963 | 0.5480 | 0.6963 | 0.8345 |
|
| 90 |
+
| No log | 0.8211 | 78 | 0.7482 | 0.5260 | 0.7482 | 0.8650 |
|
| 91 |
+
| No log | 0.8421 | 80 | 0.7119 | 0.5832 | 0.7119 | 0.8438 |
|
| 92 |
+
| No log | 0.8632 | 82 | 0.7737 | 0.5769 | 0.7737 | 0.8796 |
|
| 93 |
+
| No log | 0.8842 | 84 | 0.8216 | 0.5489 | 0.8216 | 0.9064 |
|
| 94 |
+
| No log | 0.9053 | 86 | 0.8944 | 0.5671 | 0.8944 | 0.9457 |
|
| 95 |
+
| No log | 0.9263 | 88 | 0.9017 | 0.5744 | 0.9017 | 0.9496 |
|
| 96 |
+
| No log | 0.9474 | 90 | 0.8359 | 0.5917 | 0.8359 | 0.9143 |
|
| 97 |
+
| No log | 0.9684 | 92 | 0.7722 | 0.5680 | 0.7722 | 0.8787 |
|
| 98 |
+
| No log | 0.9895 | 94 | 0.7784 | 0.6046 | 0.7784 | 0.8823 |
|
| 99 |
+
| No log | 1.0105 | 96 | 0.7992 | 0.5893 | 0.7992 | 0.8940 |
|
| 100 |
+
| No log | 1.0316 | 98 | 0.7506 | 0.5949 | 0.7506 | 0.8664 |
|
| 101 |
+
| No log | 1.0526 | 100 | 0.6970 | 0.5439 | 0.6970 | 0.8349 |
|
| 102 |
+
| No log | 1.0737 | 102 | 0.6824 | 0.5066 | 0.6824 | 0.8261 |
|
| 103 |
+
| No log | 1.0947 | 104 | 0.6653 | 0.6022 | 0.6653 | 0.8156 |
|
| 104 |
+
| No log | 1.1158 | 106 | 0.8143 | 0.6640 | 0.8143 | 0.9024 |
|
| 105 |
+
| No log | 1.1368 | 108 | 0.9773 | 0.5543 | 0.9773 | 0.9886 |
|
| 106 |
+
| No log | 1.1579 | 110 | 0.8856 | 0.5956 | 0.8856 | 0.9411 |
|
| 107 |
+
| No log | 1.1789 | 112 | 0.6787 | 0.6724 | 0.6787 | 0.8238 |
|
| 108 |
+
| No log | 1.2 | 114 | 0.6127 | 0.6125 | 0.6127 | 0.7828 |
|
| 109 |
+
| No log | 1.2211 | 116 | 0.5913 | 0.6102 | 0.5913 | 0.7689 |
|
| 110 |
+
| No log | 1.2421 | 118 | 0.5910 | 0.6685 | 0.5910 | 0.7687 |
|
| 111 |
+
| No log | 1.2632 | 120 | 0.5799 | 0.6519 | 0.5799 | 0.7615 |
|
| 112 |
+
| No log | 1.2842 | 122 | 0.6040 | 0.6766 | 0.6040 | 0.7772 |
|
| 113 |
+
| No log | 1.3053 | 124 | 0.5820 | 0.6639 | 0.5820 | 0.7629 |
|
| 114 |
+
| No log | 1.3263 | 126 | 0.6125 | 0.6455 | 0.6125 | 0.7826 |
|
| 115 |
+
| No log | 1.3474 | 128 | 0.7026 | 0.6238 | 0.7026 | 0.8382 |
|
| 116 |
+
| No log | 1.3684 | 130 | 0.7485 | 0.6731 | 0.7485 | 0.8651 |
|
| 117 |
+
| No log | 1.3895 | 132 | 0.7067 | 0.6897 | 0.7067 | 0.8407 |
|
| 118 |
+
| No log | 1.4105 | 134 | 0.6204 | 0.6852 | 0.6204 | 0.7877 |
|
| 119 |
+
| No log | 1.4316 | 136 | 0.5575 | 0.5742 | 0.5575 | 0.7467 |
|
| 120 |
+
| No log | 1.4526 | 138 | 0.5991 | 0.6302 | 0.5991 | 0.7740 |
|
| 121 |
+
| No log | 1.4737 | 140 | 0.5776 | 0.6035 | 0.5776 | 0.7600 |
|
| 122 |
+
| No log | 1.4947 | 142 | 0.6134 | 0.6692 | 0.6134 | 0.7832 |
|
| 123 |
+
| No log | 1.5158 | 144 | 0.6538 | 0.6751 | 0.6538 | 0.8086 |
|
| 124 |
+
| No log | 1.5368 | 146 | 0.6311 | 0.6988 | 0.6311 | 0.7944 |
|
| 125 |
+
| No log | 1.5579 | 148 | 0.5874 | 0.6459 | 0.5874 | 0.7664 |
|
| 126 |
+
| No log | 1.5789 | 150 | 0.5548 | 0.6356 | 0.5548 | 0.7448 |
|
| 127 |
+
| No log | 1.6 | 152 | 0.5932 | 0.6626 | 0.5932 | 0.7702 |
|
| 128 |
+
| No log | 1.6211 | 154 | 0.6156 | 0.6867 | 0.6156 | 0.7846 |
|
| 129 |
+
| No log | 1.6421 | 156 | 0.6376 | 0.6900 | 0.6376 | 0.7985 |
|
| 130 |
+
| No log | 1.6632 | 158 | 0.5900 | 0.6518 | 0.5900 | 0.7681 |
|
| 131 |
+
| No log | 1.6842 | 160 | 0.6416 | 0.6599 | 0.6416 | 0.8010 |
|
| 132 |
+
| No log | 1.7053 | 162 | 0.6472 | 0.6470 | 0.6472 | 0.8045 |
|
| 133 |
+
| No log | 1.7263 | 164 | 0.5741 | 0.6667 | 0.5741 | 0.7577 |
|
| 134 |
+
| No log | 1.7474 | 166 | 0.6198 | 0.6412 | 0.6198 | 0.7873 |
|
| 135 |
+
| No log | 1.7684 | 168 | 0.7316 | 0.6199 | 0.7316 | 0.8553 |
|
| 136 |
+
| No log | 1.7895 | 170 | 0.6742 | 0.6301 | 0.6742 | 0.8211 |
|
| 137 |
+
| No log | 1.8105 | 172 | 0.6061 | 0.6028 | 0.6061 | 0.7785 |
|
| 138 |
+
| No log | 1.8316 | 174 | 0.5636 | 0.6545 | 0.5636 | 0.7507 |
|
| 139 |
+
| No log | 1.8526 | 176 | 0.5649 | 0.6578 | 0.5649 | 0.7516 |
|
| 140 |
+
| No log | 1.8737 | 178 | 0.5744 | 0.6743 | 0.5744 | 0.7579 |
|
| 141 |
+
| No log | 1.8947 | 180 | 0.5874 | 0.7048 | 0.5874 | 0.7664 |
|
| 142 |
+
| No log | 1.9158 | 182 | 0.5879 | 0.6877 | 0.5879 | 0.7667 |
|
| 143 |
+
| No log | 1.9368 | 184 | 0.5879 | 0.6833 | 0.5879 | 0.7667 |
|
| 144 |
+
| No log | 1.9579 | 186 | 0.6152 | 0.7144 | 0.6152 | 0.7843 |
|
| 145 |
+
| No log | 1.9789 | 188 | 0.6098 | 0.6981 | 0.6098 | 0.7809 |
|
| 146 |
+
| No log | 2.0 | 190 | 0.5754 | 0.7184 | 0.5754 | 0.7585 |
|
| 147 |
+
| No log | 2.0211 | 192 | 0.5352 | 0.6704 | 0.5352 | 0.7316 |
|
| 148 |
+
| No log | 2.0421 | 194 | 0.5745 | 0.7027 | 0.5745 | 0.7579 |
|
| 149 |
+
| No log | 2.0632 | 196 | 0.6462 | 0.6554 | 0.6462 | 0.8039 |
|
| 150 |
+
| No log | 2.0842 | 198 | 0.6697 | 0.6120 | 0.6697 | 0.8184 |
|
| 151 |
+
| No log | 2.1053 | 200 | 0.6014 | 0.6628 | 0.6014 | 0.7755 |
|
| 152 |
+
| No log | 2.1263 | 202 | 0.5472 | 0.6812 | 0.5472 | 0.7397 |
|
| 153 |
+
| No log | 2.1474 | 204 | 0.5398 | 0.6981 | 0.5398 | 0.7347 |
|
| 154 |
+
| No log | 2.1684 | 206 | 0.5347 | 0.7279 | 0.5347 | 0.7312 |
|
| 155 |
+
| No log | 2.1895 | 208 | 0.5194 | 0.7216 | 0.5194 | 0.7207 |
|
| 156 |
+
| No log | 2.2105 | 210 | 0.5148 | 0.7320 | 0.5148 | 0.7175 |
|
| 157 |
+
| No log | 2.2316 | 212 | 0.5397 | 0.7180 | 0.5397 | 0.7347 |
|
| 158 |
+
| No log | 2.2526 | 214 | 0.5512 | 0.7083 | 0.5512 | 0.7424 |
|
| 159 |
+
| No log | 2.2737 | 216 | 0.6078 | 0.6828 | 0.6078 | 0.7796 |
|
| 160 |
+
| No log | 2.2947 | 218 | 0.6092 | 0.6775 | 0.6092 | 0.7805 |
|
| 161 |
+
| No log | 2.3158 | 220 | 0.6017 | 0.6324 | 0.6017 | 0.7757 |
|
| 162 |
+
| No log | 2.3368 | 222 | 0.6682 | 0.6403 | 0.6682 | 0.8174 |
|
| 163 |
+
| No log | 2.3579 | 224 | 0.7419 | 0.6436 | 0.7419 | 0.8613 |
|
| 164 |
+
| No log | 2.3789 | 226 | 0.6821 | 0.6253 | 0.6821 | 0.8259 |
|
| 165 |
+
| No log | 2.4 | 228 | 0.5920 | 0.6051 | 0.5920 | 0.7694 |
|
| 166 |
+
| No log | 2.4211 | 230 | 0.5816 | 0.6562 | 0.5816 | 0.7626 |
|
| 167 |
+
| No log | 2.4421 | 232 | 0.5854 | 0.6429 | 0.5854 | 0.7651 |
|
| 168 |
+
| No log | 2.4632 | 234 | 0.6317 | 0.5988 | 0.6317 | 0.7948 |
|
| 169 |
+
| No log | 2.4842 | 236 | 0.7165 | 0.5895 | 0.7165 | 0.8464 |
|
| 170 |
+
| No log | 2.5053 | 238 | 0.6806 | 0.6269 | 0.6806 | 0.8250 |
|
| 171 |
+
| No log | 2.5263 | 240 | 0.5810 | 0.6157 | 0.5810 | 0.7622 |
|
| 172 |
+
| No log | 2.5474 | 242 | 0.5820 | 0.6330 | 0.5820 | 0.7629 |
|
| 173 |
+
| No log | 2.5684 | 244 | 0.6124 | 0.5554 | 0.6124 | 0.7826 |
|
| 174 |
+
| No log | 2.5895 | 246 | 0.6242 | 0.5770 | 0.6242 | 0.7900 |
|
| 175 |
+
| No log | 2.6105 | 248 | 0.6023 | 0.6473 | 0.6023 | 0.7761 |
|
| 176 |
+
| No log | 2.6316 | 250 | 0.5962 | 0.6399 | 0.5962 | 0.7721 |
|
| 177 |
+
| No log | 2.6526 | 252 | 0.5711 | 0.6843 | 0.5711 | 0.7557 |
|
| 178 |
+
| No log | 2.6737 | 254 | 0.5540 | 0.7083 | 0.5540 | 0.7443 |
|
| 179 |
+
| No log | 2.6947 | 256 | 0.5459 | 0.7083 | 0.5459 | 0.7388 |
|
| 180 |
+
| No log | 2.7158 | 258 | 0.5356 | 0.7318 | 0.5356 | 0.7318 |
|
| 181 |
+
| No log | 2.7368 | 260 | 0.5244 | 0.7501 | 0.5244 | 0.7241 |
|
| 182 |
+
| No log | 2.7579 | 262 | 0.5183 | 0.7189 | 0.5183 | 0.7199 |
|
| 183 |
+
| No log | 2.7789 | 264 | 0.5408 | 0.6736 | 0.5408 | 0.7354 |
|
| 184 |
+
| No log | 2.8 | 266 | 0.5723 | 0.6781 | 0.5723 | 0.7565 |
|
| 185 |
+
| No log | 2.8211 | 268 | 0.5631 | 0.6605 | 0.5631 | 0.7504 |
|
| 186 |
+
| No log | 2.8421 | 270 | 0.5412 | 0.7119 | 0.5412 | 0.7357 |
|
| 187 |
+
| No log | 2.8632 | 272 | 0.4984 | 0.7305 | 0.4984 | 0.7060 |
|
| 188 |
+
| No log | 2.8842 | 274 | 0.4878 | 0.7314 | 0.4878 | 0.6984 |
|
| 189 |
+
| No log | 2.9053 | 276 | 0.5185 | 0.7398 | 0.5185 | 0.7200 |
|
| 190 |
+
| No log | 2.9263 | 278 | 0.5765 | 0.7020 | 0.5765 | 0.7593 |
|
| 191 |
+
| No log | 2.9474 | 280 | 0.5671 | 0.7141 | 0.5671 | 0.7530 |
|
| 192 |
+
| No log | 2.9684 | 282 | 0.5548 | 0.6805 | 0.5548 | 0.7448 |
|
| 193 |
+
| No log | 2.9895 | 284 | 0.5914 | 0.6849 | 0.5914 | 0.7690 |
|
| 194 |
+
| No log | 3.0105 | 286 | 0.6614 | 0.5777 | 0.6614 | 0.8133 |
|
| 195 |
+
| No log | 3.0316 | 288 | 0.7040 | 0.5455 | 0.7040 | 0.8390 |
|
| 196 |
+
| No log | 3.0526 | 290 | 0.8083 | 0.5704 | 0.8083 | 0.8991 |
|
| 197 |
+
| No log | 3.0737 | 292 | 0.7866 | 0.5759 | 0.7866 | 0.8869 |
|
| 198 |
+
| No log | 3.0947 | 294 | 0.7487 | 0.5948 | 0.7487 | 0.8652 |
|
| 199 |
+
| No log | 3.1158 | 296 | 0.6771 | 0.5862 | 0.6771 | 0.8229 |
|
| 200 |
+
| No log | 3.1368 | 298 | 0.6439 | 0.5776 | 0.6439 | 0.8024 |
|
| 201 |
+
| No log | 3.1579 | 300 | 0.6805 | 0.5634 | 0.6805 | 0.8249 |
|
| 202 |
+
| No log | 3.1789 | 302 | 0.6570 | 0.5543 | 0.6570 | 0.8105 |
|
| 203 |
+
| No log | 3.2 | 304 | 0.6091 | 0.6421 | 0.6091 | 0.7804 |
|
| 204 |
+
| No log | 3.2211 | 306 | 0.5980 | 0.6528 | 0.5980 | 0.7733 |
|
| 205 |
+
| No log | 3.2421 | 308 | 0.6725 | 0.6371 | 0.6725 | 0.8200 |
|
| 206 |
+
| No log | 3.2632 | 310 | 0.7828 | 0.5495 | 0.7828 | 0.8848 |
|
| 207 |
+
| No log | 3.2842 | 312 | 0.7761 | 0.5198 | 0.7761 | 0.8810 |
|
| 208 |
+
| No log | 3.3053 | 314 | 0.6841 | 0.5766 | 0.6841 | 0.8271 |
|
| 209 |
+
| No log | 3.3263 | 316 | 0.6327 | 0.5948 | 0.6327 | 0.7954 |
|
| 210 |
+
| No log | 3.3474 | 318 | 0.6538 | 0.6564 | 0.6538 | 0.8086 |
|
| 211 |
+
| No log | 3.3684 | 320 | 0.6576 | 0.6564 | 0.6576 | 0.8109 |
|
| 212 |
+
| No log | 3.3895 | 322 | 0.6877 | 0.6753 | 0.6877 | 0.8293 |
|
| 213 |
+
| No log | 3.4105 | 324 | 0.6616 | 0.6640 | 0.6616 | 0.8134 |
|
| 214 |
+
| No log | 3.4316 | 326 | 0.7597 | 0.5769 | 0.7597 | 0.8716 |
|
| 215 |
+
| No log | 3.4526 | 328 | 0.7098 | 0.5963 | 0.7098 | 0.8425 |
|
| 216 |
+
| No log | 3.4737 | 330 | 0.6021 | 0.6365 | 0.6021 | 0.7760 |
|
| 217 |
+
| No log | 3.4947 | 332 | 0.6091 | 0.6097 | 0.6091 | 0.7804 |
|
| 218 |
+
| No log | 3.5158 | 334 | 0.6204 | 0.5626 | 0.6204 | 0.7876 |
|
| 219 |
+
| No log | 3.5368 | 336 | 0.6614 | 0.5821 | 0.6614 | 0.8133 |
|
| 220 |
+
| No log | 3.5579 | 338 | 0.6837 | 0.5677 | 0.6837 | 0.8268 |
|
| 221 |
+
| No log | 3.5789 | 340 | 0.6309 | 0.5776 | 0.6309 | 0.7943 |
|
| 222 |
+
| No log | 3.6 | 342 | 0.6150 | 0.7028 | 0.6150 | 0.7842 |
|
| 223 |
+
| No log | 3.6211 | 344 | 0.6085 | 0.7265 | 0.6085 | 0.7801 |
|
| 224 |
+
| No log | 3.6421 | 346 | 0.6103 | 0.7124 | 0.6103 | 0.7812 |
|
| 225 |
+
| No log | 3.6632 | 348 | 0.6387 | 0.6556 | 0.6387 | 0.7992 |
|
| 226 |
+
| No log | 3.6842 | 350 | 0.6024 | 0.6482 | 0.6024 | 0.7761 |
|
| 227 |
+
| No log | 3.7053 | 352 | 0.5739 | 0.6221 | 0.5739 | 0.7576 |
|
| 228 |
+
| No log | 3.7263 | 354 | 0.5625 | 0.5960 | 0.5625 | 0.7500 |
|
| 229 |
+
| No log | 3.7474 | 356 | 0.5572 | 0.6065 | 0.5572 | 0.7464 |
|
| 230 |
+
| No log | 3.7684 | 358 | 0.5579 | 0.6415 | 0.5579 | 0.7470 |
|
| 231 |
+
| No log | 3.7895 | 360 | 0.6144 | 0.5875 | 0.6144 | 0.7839 |
|
| 232 |
+
| No log | 3.8105 | 362 | 0.7103 | 0.6263 | 0.7103 | 0.8428 |
|
| 233 |
+
| No log | 3.8316 | 364 | 0.7617 | 0.5849 | 0.7617 | 0.8728 |
|
| 234 |
+
| No log | 3.8526 | 366 | 0.6813 | 0.6123 | 0.6813 | 0.8254 |
|
| 235 |
+
| No log | 3.8737 | 368 | 0.5977 | 0.5730 | 0.5977 | 0.7731 |
|
| 236 |
+
| No log | 3.8947 | 370 | 0.5824 | 0.6415 | 0.5824 | 0.7631 |
|
| 237 |
+
| No log | 3.9158 | 372 | 0.6284 | 0.5719 | 0.6284 | 0.7927 |
|
| 238 |
+
| No log | 3.9368 | 374 | 0.7763 | 0.5861 | 0.7763 | 0.8811 |
|
| 239 |
+
| No log | 3.9579 | 376 | 0.8683 | 0.5526 | 0.8683 | 0.9318 |
|
| 240 |
+
| No log | 3.9789 | 378 | 0.8511 | 0.5541 | 0.8511 | 0.9226 |
|
| 241 |
+
| No log | 4.0 | 380 | 0.7707 | 0.5110 | 0.7707 | 0.8779 |
|
| 242 |
+
| No log | 4.0211 | 382 | 0.6694 | 0.5970 | 0.6694 | 0.8182 |
|
| 243 |
+
| No log | 4.0421 | 384 | 0.5965 | 0.5810 | 0.5965 | 0.7723 |
|
| 244 |
+
| No log | 4.0632 | 386 | 0.5887 | 0.5882 | 0.5887 | 0.7673 |
|
| 245 |
+
| No log | 4.0842 | 388 | 0.5731 | 0.6354 | 0.5731 | 0.7570 |
|
| 246 |
+
| No log | 4.1053 | 390 | 0.6079 | 0.5622 | 0.6079 | 0.7797 |
|
| 247 |
+
| No log | 4.1263 | 392 | 0.6360 | 0.5666 | 0.6360 | 0.7975 |
|
| 248 |
+
| No log | 4.1474 | 394 | 0.6240 | 0.6141 | 0.6240 | 0.7900 |
|
| 249 |
+
| No log | 4.1684 | 396 | 0.5423 | 0.6835 | 0.5423 | 0.7364 |
|
| 250 |
+
| No log | 4.1895 | 398 | 0.5070 | 0.7064 | 0.5070 | 0.7120 |
|
| 251 |
+
| No log | 4.2105 | 400 | 0.5184 | 0.7124 | 0.5184 | 0.7200 |
|
| 252 |
+
| No log | 4.2316 | 402 | 0.5396 | 0.6919 | 0.5396 | 0.7346 |
|
| 253 |
+
| No log | 4.2526 | 404 | 0.5273 | 0.7158 | 0.5273 | 0.7261 |
|
| 254 |
+
| No log | 4.2737 | 406 | 0.5447 | 0.6820 | 0.5447 | 0.7381 |
|
| 255 |
+
| No log | 4.2947 | 408 | 0.5644 | 0.6545 | 0.5644 | 0.7512 |
|
| 256 |
+
| No log | 4.3158 | 410 | 0.5585 | 0.6903 | 0.5585 | 0.7473 |
|
| 257 |
+
| No log | 4.3368 | 412 | 0.5702 | 0.6365 | 0.5702 | 0.7551 |
|
| 258 |
+
| No log | 4.3579 | 414 | 0.5849 | 0.6243 | 0.5849 | 0.7648 |
|
| 259 |
+
| No log | 4.3789 | 416 | 0.6017 | 0.6560 | 0.6017 | 0.7757 |
|
| 260 |
+
| No log | 4.4 | 418 | 0.5974 | 0.6536 | 0.5974 | 0.7729 |
|
| 261 |
+
| No log | 4.4211 | 420 | 0.5706 | 0.6736 | 0.5706 | 0.7554 |
|
| 262 |
+
| No log | 4.4421 | 422 | 0.5678 | 0.6888 | 0.5678 | 0.7535 |
|
| 263 |
+
| No log | 4.4632 | 424 | 0.5452 | 0.6717 | 0.5452 | 0.7384 |
|
| 264 |
+
| No log | 4.4842 | 426 | 0.5519 | 0.6476 | 0.5519 | 0.7429 |
|
| 265 |
+
| No log | 4.5053 | 428 | 0.5809 | 0.6012 | 0.5809 | 0.7622 |
|
| 266 |
+
| No log | 4.5263 | 430 | 0.5737 | 0.6028 | 0.5737 | 0.7575 |
|
| 267 |
+
| No log | 4.5474 | 432 | 0.5678 | 0.6335 | 0.5678 | 0.7535 |
|
| 268 |
+
| No log | 4.5684 | 434 | 0.5670 | 0.6370 | 0.5670 | 0.7530 |
|
| 269 |
+
| No log | 4.5895 | 436 | 0.5803 | 0.6335 | 0.5803 | 0.7618 |
|
| 270 |
+
| No log | 4.6105 | 438 | 0.6320 | 0.5566 | 0.6320 | 0.7950 |
|
| 271 |
+
| No log | 4.6316 | 440 | 0.5985 | 0.5688 | 0.5985 | 0.7736 |
|
| 272 |
+
| No log | 4.6526 | 442 | 0.5302 | 0.6853 | 0.5302 | 0.7282 |
|
| 273 |
+
| No log | 4.6737 | 444 | 0.4971 | 0.7064 | 0.4971 | 0.7051 |
|
| 274 |
+
| No log | 4.6947 | 446 | 0.4973 | 0.6935 | 0.4973 | 0.7052 |
|
| 275 |
+
| No log | 4.7158 | 448 | 0.5041 | 0.7054 | 0.5041 | 0.7100 |
|
| 276 |
+
| No log | 4.7368 | 450 | 0.5150 | 0.7294 | 0.5150 | 0.7176 |
|
| 277 |
+
| No log | 4.7579 | 452 | 0.5173 | 0.6877 | 0.5173 | 0.7192 |
|
| 278 |
+
| No log | 4.7789 | 454 | 0.5255 | 0.6680 | 0.5255 | 0.7249 |
|
| 279 |
+
| No log | 4.8 | 456 | 0.5260 | 0.6680 | 0.5260 | 0.7252 |
|
| 280 |
+
| No log | 4.8211 | 458 | 0.5206 | 0.6501 | 0.5206 | 0.7216 |
|
| 281 |
+
| No log | 4.8421 | 460 | 0.5250 | 0.6835 | 0.5250 | 0.7246 |
|
| 282 |
+
| No log | 4.8632 | 462 | 0.5130 | 0.7003 | 0.5130 | 0.7163 |
|
| 283 |
+
| No log | 4.8842 | 464 | 0.5341 | 0.6406 | 0.5341 | 0.7308 |
|
| 284 |
+
| No log | 4.9053 | 466 | 0.5450 | 0.6188 | 0.5450 | 0.7382 |
|
| 285 |
+
| No log | 4.9263 | 468 | 0.5599 | 0.6520 | 0.5599 | 0.7483 |
|
| 286 |
+
| No log | 4.9474 | 470 | 0.5976 | 0.6225 | 0.5976 | 0.7730 |
|
| 287 |
+
| No log | 4.9684 | 472 | 0.5526 | 0.6476 | 0.5526 | 0.7434 |
|
| 288 |
+
| No log | 4.9895 | 474 | 0.5349 | 0.6756 | 0.5349 | 0.7313 |
|
| 289 |
+
| No log | 5.0105 | 476 | 0.5444 | 0.6938 | 0.5444 | 0.7378 |
|
| 290 |
+
| No log | 5.0316 | 478 | 0.5439 | 0.6568 | 0.5439 | 0.7375 |
|
| 291 |
+
| No log | 5.0526 | 480 | 0.5801 | 0.6753 | 0.5801 | 0.7616 |
|
| 292 |
+
| No log | 5.0737 | 482 | 0.7030 | 0.6260 | 0.7030 | 0.8384 |
|
| 293 |
+
| No log | 5.0947 | 484 | 0.7308 | 0.6439 | 0.7308 | 0.8549 |
|
| 294 |
+
| No log | 5.1158 | 486 | 0.6374 | 0.5930 | 0.6374 | 0.7984 |
|
| 295 |
+
| No log | 5.1368 | 488 | 0.5605 | 0.6476 | 0.5605 | 0.7487 |
|
| 296 |
+
| No log | 5.1579 | 490 | 0.5499 | 0.6602 | 0.5499 | 0.7415 |
|
| 297 |
+
| No log | 5.1789 | 492 | 0.5551 | 0.6572 | 0.5551 | 0.7450 |
|
| 298 |
+
| No log | 5.2 | 494 | 0.5499 | 0.6820 | 0.5499 | 0.7416 |
|
| 299 |
+
| No log | 5.2211 | 496 | 0.5854 | 0.6169 | 0.5854 | 0.7651 |
|
| 300 |
+
| No log | 5.2421 | 498 | 0.6682 | 0.6115 | 0.6682 | 0.8174 |
|
| 301 |
+
| 0.3146 | 5.2632 | 500 | 0.7250 | 0.6235 | 0.7250 | 0.8515 |
|
| 302 |
+
| 0.3146 | 5.2842 | 502 | 0.6909 | 0.6301 | 0.6909 | 0.8312 |
|
| 303 |
+
| 0.3146 | 5.3053 | 504 | 0.6623 | 0.6309 | 0.6623 | 0.8138 |
|
| 304 |
+
| 0.3146 | 5.3263 | 506 | 0.6058 | 0.5766 | 0.6058 | 0.7784 |
|
| 305 |
+
| 0.3146 | 5.3474 | 508 | 0.5627 | 0.6501 | 0.5627 | 0.7501 |
|
| 306 |
+
| 0.3146 | 5.3684 | 510 | 0.5597 | 0.6501 | 0.5597 | 0.7481 |
|
| 307 |
+
| 0.3146 | 5.3895 | 512 | 0.5917 | 0.5953 | 0.5917 | 0.7692 |
|
| 308 |
+
| 0.3146 | 5.4105 | 514 | 0.6606 | 0.6019 | 0.6606 | 0.8127 |
|
| 309 |
+
| 0.3146 | 5.4316 | 516 | 0.7507 | 0.6260 | 0.7507 | 0.8664 |
|
| 310 |
+
| 0.3146 | 5.4526 | 518 | 0.8735 | 0.5965 | 0.8735 | 0.9346 |
|
| 311 |
+
| 0.3146 | 5.4737 | 520 | 0.8611 | 0.6011 | 0.8611 | 0.9280 |
|
| 312 |
+
| 0.3146 | 5.4947 | 522 | 0.7846 | 0.4987 | 0.7846 | 0.8857 |
|
| 313 |
+
| 0.3146 | 5.5158 | 524 | 0.6931 | 0.5346 | 0.6931 | 0.8325 |
|
| 314 |
+
| 0.3146 | 5.5368 | 526 | 0.6533 | 0.5579 | 0.6533 | 0.8082 |
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
### Framework versions
|
| 318 |
+
|
| 319 |
+
- Transformers 4.44.2
|
| 320 |
+
- Pytorch 2.4.0+cu118
|
| 321 |
+
- Datasets 2.21.0
|
| 322 |
+
- 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 sha256:52cd0b1ebc031b5f9500b3a1403b06060145c5a23a46e39b2e74eff8267b1cfe
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e69988f89dba1bb152ca011f8a6ad45cfd7ca64179ebaeff87cbb7e84c8e440
|
| 3 |
+
size 5304
|