Training in progress, step 500
Browse files- README.md +316 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k9_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_run2_AugV5_k9_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: 0.6483
|
| 19 |
+
- Qwk: 0.5845
|
| 20 |
+
- Mse: 0.6483
|
| 21 |
+
- Rmse: 0.8052
|
| 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 | 0.0444 | 2 | 4.3123 | 0.0045 | 4.3123 | 2.0766 |
|
| 53 |
+
| No log | 0.0889 | 4 | 2.0687 | 0.1342 | 2.0687 | 1.4383 |
|
| 54 |
+
| No log | 0.1333 | 6 | 1.7422 | 0.1128 | 1.7422 | 1.3199 |
|
| 55 |
+
| No log | 0.1778 | 8 | 1.9567 | 0.1240 | 1.9567 | 1.3988 |
|
| 56 |
+
| No log | 0.2222 | 10 | 1.8315 | 0.1266 | 1.8315 | 1.3533 |
|
| 57 |
+
| No log | 0.2667 | 12 | 0.9228 | 0.3627 | 0.9228 | 0.9606 |
|
| 58 |
+
| No log | 0.3111 | 14 | 0.8345 | 0.3464 | 0.8345 | 0.9135 |
|
| 59 |
+
| No log | 0.3556 | 16 | 0.9507 | 0.2724 | 0.9507 | 0.9750 |
|
| 60 |
+
| No log | 0.4 | 18 | 0.8842 | 0.2599 | 0.8842 | 0.9403 |
|
| 61 |
+
| No log | 0.4444 | 20 | 0.8325 | 0.2921 | 0.8325 | 0.9124 |
|
| 62 |
+
| No log | 0.4889 | 22 | 0.8960 | 0.3734 | 0.8960 | 0.9465 |
|
| 63 |
+
| No log | 0.5333 | 24 | 0.9824 | 0.4394 | 0.9824 | 0.9912 |
|
| 64 |
+
| No log | 0.5778 | 26 | 0.9146 | 0.4186 | 0.9146 | 0.9563 |
|
| 65 |
+
| No log | 0.6222 | 28 | 0.7729 | 0.4596 | 0.7729 | 0.8791 |
|
| 66 |
+
| No log | 0.6667 | 30 | 0.7110 | 0.6421 | 0.7110 | 0.8432 |
|
| 67 |
+
| No log | 0.7111 | 32 | 0.7247 | 0.5683 | 0.7247 | 0.8513 |
|
| 68 |
+
| No log | 0.7556 | 34 | 0.9069 | 0.5260 | 0.9069 | 0.9523 |
|
| 69 |
+
| No log | 0.8 | 36 | 1.2492 | 0.4740 | 1.2492 | 1.1177 |
|
| 70 |
+
| No log | 0.8444 | 38 | 1.2287 | 0.4541 | 1.2287 | 1.1084 |
|
| 71 |
+
| No log | 0.8889 | 40 | 1.0033 | 0.4777 | 1.0033 | 1.0017 |
|
| 72 |
+
| No log | 0.9333 | 42 | 0.7775 | 0.4934 | 0.7775 | 0.8818 |
|
| 73 |
+
| No log | 0.9778 | 44 | 0.6460 | 0.6244 | 0.6460 | 0.8037 |
|
| 74 |
+
| No log | 1.0222 | 46 | 0.6378 | 0.6341 | 0.6378 | 0.7986 |
|
| 75 |
+
| No log | 1.0667 | 48 | 0.6382 | 0.6740 | 0.6382 | 0.7989 |
|
| 76 |
+
| No log | 1.1111 | 50 | 0.6373 | 0.6278 | 0.6373 | 0.7983 |
|
| 77 |
+
| No log | 1.1556 | 52 | 0.7294 | 0.6434 | 0.7294 | 0.8540 |
|
| 78 |
+
| No log | 1.2 | 54 | 0.8851 | 0.5516 | 0.8851 | 0.9408 |
|
| 79 |
+
| No log | 1.2444 | 56 | 0.8282 | 0.6070 | 0.8282 | 0.9100 |
|
| 80 |
+
| No log | 1.2889 | 58 | 0.8269 | 0.5922 | 0.8269 | 0.9093 |
|
| 81 |
+
| No log | 1.3333 | 60 | 0.8032 | 0.5621 | 0.8032 | 0.8962 |
|
| 82 |
+
| No log | 1.3778 | 62 | 0.7726 | 0.5617 | 0.7726 | 0.8790 |
|
| 83 |
+
| No log | 1.4222 | 64 | 0.6743 | 0.5969 | 0.6743 | 0.8212 |
|
| 84 |
+
| No log | 1.4667 | 66 | 0.6907 | 0.6056 | 0.6907 | 0.8311 |
|
| 85 |
+
| No log | 1.5111 | 68 | 0.6768 | 0.6402 | 0.6768 | 0.8227 |
|
| 86 |
+
| No log | 1.5556 | 70 | 0.7333 | 0.5772 | 0.7333 | 0.8563 |
|
| 87 |
+
| No log | 1.6 | 72 | 0.8352 | 0.5685 | 0.8352 | 0.9139 |
|
| 88 |
+
| No log | 1.6444 | 74 | 0.7533 | 0.6217 | 0.7533 | 0.8679 |
|
| 89 |
+
| No log | 1.6889 | 76 | 0.6726 | 0.6194 | 0.6726 | 0.8201 |
|
| 90 |
+
| No log | 1.7333 | 78 | 0.8159 | 0.5444 | 0.8159 | 0.9033 |
|
| 91 |
+
| No log | 1.7778 | 80 | 0.9110 | 0.5363 | 0.9110 | 0.9545 |
|
| 92 |
+
| No log | 1.8222 | 82 | 0.8795 | 0.5455 | 0.8795 | 0.9378 |
|
| 93 |
+
| No log | 1.8667 | 84 | 0.7850 | 0.6266 | 0.7850 | 0.8860 |
|
| 94 |
+
| No log | 1.9111 | 86 | 0.7449 | 0.6255 | 0.7449 | 0.8631 |
|
| 95 |
+
| No log | 1.9556 | 88 | 0.8271 | 0.6258 | 0.8271 | 0.9094 |
|
| 96 |
+
| No log | 2.0 | 90 | 0.8442 | 0.5888 | 0.8442 | 0.9188 |
|
| 97 |
+
| No log | 2.0444 | 92 | 0.7095 | 0.6502 | 0.7095 | 0.8423 |
|
| 98 |
+
| No log | 2.0889 | 94 | 0.6898 | 0.6427 | 0.6898 | 0.8305 |
|
| 99 |
+
| No log | 2.1333 | 96 | 0.6507 | 0.6597 | 0.6507 | 0.8067 |
|
| 100 |
+
| No log | 2.1778 | 98 | 0.6478 | 0.5945 | 0.6478 | 0.8049 |
|
| 101 |
+
| No log | 2.2222 | 100 | 0.6348 | 0.6350 | 0.6348 | 0.7968 |
|
| 102 |
+
| No log | 2.2667 | 102 | 0.6380 | 0.6350 | 0.6380 | 0.7987 |
|
| 103 |
+
| No log | 2.3111 | 104 | 0.6859 | 0.6099 | 0.6859 | 0.8282 |
|
| 104 |
+
| No log | 2.3556 | 106 | 0.6524 | 0.6636 | 0.6524 | 0.8077 |
|
| 105 |
+
| No log | 2.4 | 108 | 0.6303 | 0.6693 | 0.6303 | 0.7939 |
|
| 106 |
+
| No log | 2.4444 | 110 | 0.6384 | 0.6701 | 0.6384 | 0.7990 |
|
| 107 |
+
| No log | 2.4889 | 112 | 0.6756 | 0.6284 | 0.6756 | 0.8220 |
|
| 108 |
+
| No log | 2.5333 | 114 | 0.7000 | 0.6406 | 0.7000 | 0.8367 |
|
| 109 |
+
| No log | 2.5778 | 116 | 0.7673 | 0.6002 | 0.7673 | 0.8759 |
|
| 110 |
+
| No log | 2.6222 | 118 | 0.8423 | 0.5789 | 0.8423 | 0.9178 |
|
| 111 |
+
| No log | 2.6667 | 120 | 0.8007 | 0.5807 | 0.8007 | 0.8948 |
|
| 112 |
+
| No log | 2.7111 | 122 | 0.7074 | 0.5849 | 0.7074 | 0.8411 |
|
| 113 |
+
| No log | 2.7556 | 124 | 0.7799 | 0.5245 | 0.7799 | 0.8831 |
|
| 114 |
+
| No log | 2.8 | 126 | 0.7450 | 0.4998 | 0.7450 | 0.8631 |
|
| 115 |
+
| No log | 2.8444 | 128 | 0.6752 | 0.6087 | 0.6752 | 0.8217 |
|
| 116 |
+
| No log | 2.8889 | 130 | 0.7176 | 0.6013 | 0.7176 | 0.8471 |
|
| 117 |
+
| No log | 2.9333 | 132 | 0.7414 | 0.5537 | 0.7414 | 0.8611 |
|
| 118 |
+
| No log | 2.9778 | 134 | 0.7748 | 0.6975 | 0.7748 | 0.8802 |
|
| 119 |
+
| No log | 3.0222 | 136 | 0.9055 | 0.5562 | 0.9055 | 0.9516 |
|
| 120 |
+
| No log | 3.0667 | 138 | 0.9198 | 0.5733 | 0.9198 | 0.9590 |
|
| 121 |
+
| No log | 3.1111 | 140 | 0.8119 | 0.6226 | 0.8119 | 0.9010 |
|
| 122 |
+
| No log | 3.1556 | 142 | 0.7130 | 0.6026 | 0.7130 | 0.8444 |
|
| 123 |
+
| No log | 3.2 | 144 | 0.7200 | 0.6227 | 0.7200 | 0.8485 |
|
| 124 |
+
| No log | 3.2444 | 146 | 0.7633 | 0.5735 | 0.7633 | 0.8737 |
|
| 125 |
+
| No log | 3.2889 | 148 | 0.6663 | 0.6257 | 0.6663 | 0.8163 |
|
| 126 |
+
| No log | 3.3333 | 150 | 0.6513 | 0.5158 | 0.6513 | 0.8070 |
|
| 127 |
+
| No log | 3.3778 | 152 | 0.7966 | 0.5552 | 0.7966 | 0.8925 |
|
| 128 |
+
| No log | 3.4222 | 154 | 0.8317 | 0.5547 | 0.8317 | 0.9120 |
|
| 129 |
+
| No log | 3.4667 | 156 | 0.8186 | 0.5510 | 0.8186 | 0.9048 |
|
| 130 |
+
| No log | 3.5111 | 158 | 0.7708 | 0.6689 | 0.7708 | 0.8780 |
|
| 131 |
+
| No log | 3.5556 | 160 | 0.7528 | 0.6456 | 0.7528 | 0.8676 |
|
| 132 |
+
| No log | 3.6 | 162 | 0.7185 | 0.5824 | 0.7185 | 0.8477 |
|
| 133 |
+
| No log | 3.6444 | 164 | 0.6587 | 0.6134 | 0.6587 | 0.8116 |
|
| 134 |
+
| No log | 3.6889 | 166 | 0.6558 | 0.6039 | 0.6558 | 0.8098 |
|
| 135 |
+
| No log | 3.7333 | 168 | 0.6515 | 0.5990 | 0.6515 | 0.8071 |
|
| 136 |
+
| No log | 3.7778 | 170 | 0.7011 | 0.6536 | 0.7011 | 0.8373 |
|
| 137 |
+
| No log | 3.8222 | 172 | 0.7423 | 0.6294 | 0.7423 | 0.8615 |
|
| 138 |
+
| No log | 3.8667 | 174 | 0.7435 | 0.6094 | 0.7435 | 0.8623 |
|
| 139 |
+
| No log | 3.9111 | 176 | 0.7170 | 0.5713 | 0.7170 | 0.8467 |
|
| 140 |
+
| No log | 3.9556 | 178 | 0.7469 | 0.5209 | 0.7469 | 0.8642 |
|
| 141 |
+
| No log | 4.0 | 180 | 0.7316 | 0.4657 | 0.7316 | 0.8553 |
|
| 142 |
+
| No log | 4.0444 | 182 | 0.6840 | 0.6016 | 0.6840 | 0.8270 |
|
| 143 |
+
| No log | 4.0889 | 184 | 0.6816 | 0.6197 | 0.6816 | 0.8256 |
|
| 144 |
+
| No log | 4.1333 | 186 | 0.6746 | 0.5818 | 0.6746 | 0.8213 |
|
| 145 |
+
| No log | 4.1778 | 188 | 0.6885 | 0.6272 | 0.6885 | 0.8297 |
|
| 146 |
+
| No log | 4.2222 | 190 | 0.7473 | 0.5759 | 0.7473 | 0.8645 |
|
| 147 |
+
| No log | 4.2667 | 192 | 0.7126 | 0.6418 | 0.7126 | 0.8442 |
|
| 148 |
+
| No log | 4.3111 | 194 | 0.6834 | 0.6266 | 0.6834 | 0.8267 |
|
| 149 |
+
| No log | 4.3556 | 196 | 0.7127 | 0.5652 | 0.7127 | 0.8442 |
|
| 150 |
+
| No log | 4.4 | 198 | 0.6786 | 0.5958 | 0.6786 | 0.8238 |
|
| 151 |
+
| No log | 4.4444 | 200 | 0.6648 | 0.6318 | 0.6648 | 0.8153 |
|
| 152 |
+
| No log | 4.4889 | 202 | 0.7741 | 0.6131 | 0.7741 | 0.8798 |
|
| 153 |
+
| No log | 4.5333 | 204 | 0.8463 | 0.6315 | 0.8463 | 0.9199 |
|
| 154 |
+
| No log | 4.5778 | 206 | 0.7567 | 0.6694 | 0.7567 | 0.8699 |
|
| 155 |
+
| No log | 4.6222 | 208 | 0.7253 | 0.6694 | 0.7253 | 0.8516 |
|
| 156 |
+
| No log | 4.6667 | 210 | 0.6684 | 0.6202 | 0.6684 | 0.8175 |
|
| 157 |
+
| No log | 4.7111 | 212 | 0.6393 | 0.5865 | 0.6393 | 0.7996 |
|
| 158 |
+
| No log | 4.7556 | 214 | 0.6263 | 0.6259 | 0.6263 | 0.7914 |
|
| 159 |
+
| No log | 4.8 | 216 | 0.6282 | 0.6464 | 0.6282 | 0.7926 |
|
| 160 |
+
| No log | 4.8444 | 218 | 0.6383 | 0.6092 | 0.6383 | 0.7989 |
|
| 161 |
+
| No log | 4.8889 | 220 | 0.6692 | 0.5508 | 0.6692 | 0.8180 |
|
| 162 |
+
| No log | 4.9333 | 222 | 0.6887 | 0.6010 | 0.6887 | 0.8299 |
|
| 163 |
+
| No log | 4.9778 | 224 | 0.6813 | 0.5931 | 0.6813 | 0.8254 |
|
| 164 |
+
| No log | 5.0222 | 226 | 0.6536 | 0.6138 | 0.6536 | 0.8085 |
|
| 165 |
+
| No log | 5.0667 | 228 | 0.6511 | 0.6446 | 0.6511 | 0.8069 |
|
| 166 |
+
| No log | 5.1111 | 230 | 0.6587 | 0.6609 | 0.6587 | 0.8116 |
|
| 167 |
+
| No log | 5.1556 | 232 | 0.6680 | 0.6609 | 0.6680 | 0.8173 |
|
| 168 |
+
| No log | 5.2 | 234 | 0.6462 | 0.6500 | 0.6462 | 0.8039 |
|
| 169 |
+
| No log | 5.2444 | 236 | 0.6689 | 0.5945 | 0.6689 | 0.8178 |
|
| 170 |
+
| No log | 5.2889 | 238 | 0.6984 | 0.5636 | 0.6984 | 0.8357 |
|
| 171 |
+
| No log | 5.3333 | 240 | 0.7145 | 0.5837 | 0.7145 | 0.8453 |
|
| 172 |
+
| No log | 5.3778 | 242 | 0.6977 | 0.6166 | 0.6977 | 0.8353 |
|
| 173 |
+
| No log | 5.4222 | 244 | 0.6843 | 0.6260 | 0.6843 | 0.8272 |
|
| 174 |
+
| No log | 5.4667 | 246 | 0.6602 | 0.6695 | 0.6602 | 0.8125 |
|
| 175 |
+
| No log | 5.5111 | 248 | 0.6494 | 0.5909 | 0.6494 | 0.8058 |
|
| 176 |
+
| No log | 5.5556 | 250 | 0.6480 | 0.5964 | 0.6480 | 0.8050 |
|
| 177 |
+
| No log | 5.6 | 252 | 0.6563 | 0.5376 | 0.6563 | 0.8101 |
|
| 178 |
+
| No log | 5.6444 | 254 | 0.6646 | 0.5596 | 0.6646 | 0.8152 |
|
| 179 |
+
| No log | 5.6889 | 256 | 0.6815 | 0.5936 | 0.6815 | 0.8255 |
|
| 180 |
+
| No log | 5.7333 | 258 | 0.6727 | 0.5804 | 0.6727 | 0.8202 |
|
| 181 |
+
| No log | 5.7778 | 260 | 0.6815 | 0.6092 | 0.6815 | 0.8256 |
|
| 182 |
+
| No log | 5.8222 | 262 | 0.8002 | 0.6112 | 0.8002 | 0.8946 |
|
| 183 |
+
| No log | 5.8667 | 264 | 0.8330 | 0.5910 | 0.8330 | 0.9127 |
|
| 184 |
+
| No log | 5.9111 | 266 | 0.7175 | 0.5569 | 0.7175 | 0.8471 |
|
| 185 |
+
| No log | 5.9556 | 268 | 0.7462 | 0.5922 | 0.7462 | 0.8638 |
|
| 186 |
+
| No log | 6.0 | 270 | 0.9487 | 0.5526 | 0.9487 | 0.9740 |
|
| 187 |
+
| No log | 6.0444 | 272 | 0.9134 | 0.5617 | 0.9134 | 0.9557 |
|
| 188 |
+
| No log | 6.0889 | 274 | 0.7302 | 0.5835 | 0.7302 | 0.8545 |
|
| 189 |
+
| No log | 6.1333 | 276 | 0.6766 | 0.6187 | 0.6766 | 0.8226 |
|
| 190 |
+
| No log | 6.1778 | 278 | 0.7501 | 0.6249 | 0.7501 | 0.8661 |
|
| 191 |
+
| No log | 6.2222 | 280 | 0.7404 | 0.6199 | 0.7404 | 0.8605 |
|
| 192 |
+
| No log | 6.2667 | 282 | 0.6876 | 0.6014 | 0.6876 | 0.8292 |
|
| 193 |
+
| No log | 6.3111 | 284 | 0.6469 | 0.6252 | 0.6469 | 0.8043 |
|
| 194 |
+
| No log | 6.3556 | 286 | 0.6306 | 0.6094 | 0.6306 | 0.7941 |
|
| 195 |
+
| No log | 6.4 | 288 | 0.6186 | 0.6011 | 0.6186 | 0.7865 |
|
| 196 |
+
| No log | 6.4444 | 290 | 0.6723 | 0.6062 | 0.6723 | 0.8199 |
|
| 197 |
+
| No log | 6.4889 | 292 | 0.7292 | 0.6154 | 0.7292 | 0.8540 |
|
| 198 |
+
| No log | 6.5333 | 294 | 0.7270 | 0.6154 | 0.7270 | 0.8527 |
|
| 199 |
+
| No log | 6.5778 | 296 | 0.7075 | 0.5961 | 0.7075 | 0.8411 |
|
| 200 |
+
| No log | 6.6222 | 298 | 0.6709 | 0.5607 | 0.6709 | 0.8191 |
|
| 201 |
+
| No log | 6.6667 | 300 | 0.6777 | 0.6059 | 0.6777 | 0.8232 |
|
| 202 |
+
| No log | 6.7111 | 302 | 0.7046 | 0.6263 | 0.7046 | 0.8394 |
|
| 203 |
+
| No log | 6.7556 | 304 | 0.6937 | 0.6059 | 0.6937 | 0.8329 |
|
| 204 |
+
| No log | 6.8 | 306 | 0.6871 | 0.5752 | 0.6871 | 0.8289 |
|
| 205 |
+
| No log | 6.8444 | 308 | 0.6800 | 0.5483 | 0.6800 | 0.8246 |
|
| 206 |
+
| No log | 6.8889 | 310 | 0.6869 | 0.5409 | 0.6869 | 0.8288 |
|
| 207 |
+
| No log | 6.9333 | 312 | 0.6842 | 0.5483 | 0.6842 | 0.8272 |
|
| 208 |
+
| No log | 6.9778 | 314 | 0.6932 | 0.5466 | 0.6932 | 0.8326 |
|
| 209 |
+
| No log | 7.0222 | 316 | 0.7056 | 0.6406 | 0.7056 | 0.8400 |
|
| 210 |
+
| No log | 7.0667 | 318 | 0.7041 | 0.6399 | 0.7041 | 0.8391 |
|
| 211 |
+
| No log | 7.1111 | 320 | 0.6820 | 0.5474 | 0.6820 | 0.8259 |
|
| 212 |
+
| No log | 7.1556 | 322 | 0.6716 | 0.5773 | 0.6716 | 0.8195 |
|
| 213 |
+
| No log | 7.2 | 324 | 0.6682 | 0.5381 | 0.6682 | 0.8174 |
|
| 214 |
+
| No log | 7.2444 | 326 | 0.6720 | 0.5731 | 0.6720 | 0.8198 |
|
| 215 |
+
| No log | 7.2889 | 328 | 0.6800 | 0.5055 | 0.6800 | 0.8247 |
|
| 216 |
+
| No log | 7.3333 | 330 | 0.6870 | 0.5483 | 0.6870 | 0.8288 |
|
| 217 |
+
| No log | 7.3778 | 332 | 0.6873 | 0.5680 | 0.6873 | 0.8290 |
|
| 218 |
+
| No log | 7.4222 | 334 | 0.6931 | 0.5602 | 0.6931 | 0.8325 |
|
| 219 |
+
| No log | 7.4667 | 336 | 0.6905 | 0.5402 | 0.6905 | 0.8310 |
|
| 220 |
+
| No log | 7.5111 | 338 | 0.6904 | 0.5602 | 0.6904 | 0.8309 |
|
| 221 |
+
| No log | 7.5556 | 340 | 0.6884 | 0.6237 | 0.6884 | 0.8297 |
|
| 222 |
+
| No log | 7.6 | 342 | 0.7033 | 0.5756 | 0.7033 | 0.8386 |
|
| 223 |
+
| No log | 7.6444 | 344 | 0.6748 | 0.6284 | 0.6748 | 0.8214 |
|
| 224 |
+
| No log | 7.6889 | 346 | 0.6367 | 0.6537 | 0.6367 | 0.7980 |
|
| 225 |
+
| No log | 7.7333 | 348 | 0.6415 | 0.5879 | 0.6415 | 0.8010 |
|
| 226 |
+
| No log | 7.7778 | 350 | 0.6480 | 0.5759 | 0.6480 | 0.8050 |
|
| 227 |
+
| No log | 7.8222 | 352 | 0.6202 | 0.5817 | 0.6202 | 0.7875 |
|
| 228 |
+
| No log | 7.8667 | 354 | 0.6179 | 0.6562 | 0.6179 | 0.7860 |
|
| 229 |
+
| No log | 7.9111 | 356 | 0.6424 | 0.6554 | 0.6424 | 0.8015 |
|
| 230 |
+
| No log | 7.9556 | 358 | 0.6162 | 0.6628 | 0.6162 | 0.7850 |
|
| 231 |
+
| No log | 8.0 | 360 | 0.6047 | 0.6610 | 0.6047 | 0.7777 |
|
| 232 |
+
| No log | 8.0444 | 362 | 0.6150 | 0.6207 | 0.6150 | 0.7842 |
|
| 233 |
+
| No log | 8.0889 | 364 | 0.6359 | 0.5856 | 0.6359 | 0.7975 |
|
| 234 |
+
| No log | 8.1333 | 366 | 0.6474 | 0.5856 | 0.6474 | 0.8046 |
|
| 235 |
+
| No log | 8.1778 | 368 | 0.6423 | 0.5856 | 0.6423 | 0.8014 |
|
| 236 |
+
| No log | 8.2222 | 370 | 0.6445 | 0.5735 | 0.6445 | 0.8028 |
|
| 237 |
+
| No log | 8.2667 | 372 | 0.6665 | 0.5820 | 0.6665 | 0.8164 |
|
| 238 |
+
| No log | 8.3111 | 374 | 0.7207 | 0.6128 | 0.7207 | 0.8489 |
|
| 239 |
+
| No log | 8.3556 | 376 | 0.8277 | 0.5581 | 0.8277 | 0.9098 |
|
| 240 |
+
| No log | 8.4 | 378 | 0.8821 | 0.5283 | 0.8821 | 0.9392 |
|
| 241 |
+
| No log | 8.4444 | 380 | 0.8005 | 0.5113 | 0.8005 | 0.8947 |
|
| 242 |
+
| No log | 8.4889 | 382 | 0.6761 | 0.5877 | 0.6761 | 0.8223 |
|
| 243 |
+
| No log | 8.5333 | 384 | 0.6532 | 0.5647 | 0.6532 | 0.8082 |
|
| 244 |
+
| No log | 8.5778 | 386 | 0.6727 | 0.6217 | 0.6727 | 0.8202 |
|
| 245 |
+
| No log | 8.6222 | 388 | 0.6497 | 0.6217 | 0.6497 | 0.8060 |
|
| 246 |
+
| No log | 8.6667 | 390 | 0.6205 | 0.5856 | 0.6205 | 0.7877 |
|
| 247 |
+
| No log | 8.7111 | 392 | 0.6345 | 0.6138 | 0.6345 | 0.7966 |
|
| 248 |
+
| No log | 8.7556 | 394 | 0.7053 | 0.5948 | 0.7053 | 0.8398 |
|
| 249 |
+
| No log | 8.8 | 396 | 0.7007 | 0.5380 | 0.7007 | 0.8371 |
|
| 250 |
+
| No log | 8.8444 | 398 | 0.6478 | 0.5610 | 0.6478 | 0.8049 |
|
| 251 |
+
| No log | 8.8889 | 400 | 0.6167 | 0.5735 | 0.6167 | 0.7853 |
|
| 252 |
+
| No log | 8.9333 | 402 | 0.6155 | 0.6429 | 0.6155 | 0.7846 |
|
| 253 |
+
| No log | 8.9778 | 404 | 0.6160 | 0.6456 | 0.6160 | 0.7849 |
|
| 254 |
+
| No log | 9.0222 | 406 | 0.5904 | 0.5977 | 0.5904 | 0.7684 |
|
| 255 |
+
| No log | 9.0667 | 408 | 0.5981 | 0.6356 | 0.5981 | 0.7734 |
|
| 256 |
+
| No log | 9.1111 | 410 | 0.6305 | 0.6589 | 0.6305 | 0.7941 |
|
| 257 |
+
| No log | 9.1556 | 412 | 0.6335 | 0.6421 | 0.6335 | 0.7959 |
|
| 258 |
+
| No log | 9.2 | 414 | 0.6206 | 0.5614 | 0.6206 | 0.7878 |
|
| 259 |
+
| No log | 9.2444 | 416 | 0.6182 | 0.6564 | 0.6182 | 0.7863 |
|
| 260 |
+
| No log | 9.2889 | 418 | 0.6371 | 0.6412 | 0.6371 | 0.7982 |
|
| 261 |
+
| No log | 9.3333 | 420 | 0.6401 | 0.5809 | 0.6401 | 0.8000 |
|
| 262 |
+
| No log | 9.3778 | 422 | 0.6111 | 0.5820 | 0.6111 | 0.7817 |
|
| 263 |
+
| No log | 9.4222 | 424 | 0.6038 | 0.6634 | 0.6038 | 0.7770 |
|
| 264 |
+
| No log | 9.4667 | 426 | 0.6004 | 0.6581 | 0.6004 | 0.7748 |
|
| 265 |
+
| No log | 9.5111 | 428 | 0.6274 | 0.5966 | 0.6274 | 0.7921 |
|
| 266 |
+
| No log | 9.5556 | 430 | 0.6439 | 0.6253 | 0.6439 | 0.8024 |
|
| 267 |
+
| No log | 9.6 | 432 | 0.6252 | 0.6244 | 0.6252 | 0.7907 |
|
| 268 |
+
| No log | 9.6444 | 434 | 0.6049 | 0.6493 | 0.6049 | 0.7778 |
|
| 269 |
+
| No log | 9.6889 | 436 | 0.6452 | 0.6728 | 0.6452 | 0.8032 |
|
| 270 |
+
| No log | 9.7333 | 438 | 0.6660 | 0.6555 | 0.6660 | 0.8161 |
|
| 271 |
+
| No log | 9.7778 | 440 | 0.6593 | 0.6464 | 0.6593 | 0.8120 |
|
| 272 |
+
| No log | 9.8222 | 442 | 0.6748 | 0.6464 | 0.6748 | 0.8214 |
|
| 273 |
+
| No log | 9.8667 | 444 | 0.6729 | 0.6235 | 0.6729 | 0.8203 |
|
| 274 |
+
| No log | 9.9111 | 446 | 0.6701 | 0.5662 | 0.6701 | 0.8186 |
|
| 275 |
+
| No log | 9.9556 | 448 | 0.6761 | 0.5888 | 0.6761 | 0.8223 |
|
| 276 |
+
| No log | 10.0 | 450 | 0.6767 | 0.5679 | 0.6767 | 0.8226 |
|
| 277 |
+
| No log | 10.0444 | 452 | 0.6663 | 0.5975 | 0.6663 | 0.8163 |
|
| 278 |
+
| No log | 10.0889 | 454 | 0.6799 | 0.6455 | 0.6799 | 0.8246 |
|
| 279 |
+
| No log | 10.1333 | 456 | 0.6761 | 0.6066 | 0.6761 | 0.8222 |
|
| 280 |
+
| No log | 10.1778 | 458 | 0.6898 | 0.6055 | 0.6898 | 0.8305 |
|
| 281 |
+
| No log | 10.2222 | 460 | 0.6835 | 0.5954 | 0.6835 | 0.8267 |
|
| 282 |
+
| No log | 10.2667 | 462 | 0.6757 | 0.5954 | 0.6757 | 0.8220 |
|
| 283 |
+
| No log | 10.3111 | 464 | 0.6656 | 0.5796 | 0.6656 | 0.8158 |
|
| 284 |
+
| No log | 10.3556 | 466 | 0.6762 | 0.5594 | 0.6762 | 0.8223 |
|
| 285 |
+
| No log | 10.4 | 468 | 0.6937 | 0.5774 | 0.6937 | 0.8329 |
|
| 286 |
+
| No log | 10.4444 | 470 | 0.7288 | 0.5853 | 0.7288 | 0.8537 |
|
| 287 |
+
| No log | 10.4889 | 472 | 0.7221 | 0.5701 | 0.7221 | 0.8498 |
|
| 288 |
+
| No log | 10.5333 | 474 | 0.6906 | 0.5614 | 0.6906 | 0.8310 |
|
| 289 |
+
| No log | 10.5778 | 476 | 0.6846 | 0.5735 | 0.6846 | 0.8274 |
|
| 290 |
+
| No log | 10.6222 | 478 | 0.6788 | 0.5735 | 0.6788 | 0.8239 |
|
| 291 |
+
| No log | 10.6667 | 480 | 0.6913 | 0.5120 | 0.6913 | 0.8314 |
|
| 292 |
+
| No log | 10.7111 | 482 | 0.7242 | 0.6318 | 0.7242 | 0.8510 |
|
| 293 |
+
| No log | 10.7556 | 484 | 0.7210 | 0.6479 | 0.7210 | 0.8491 |
|
| 294 |
+
| No log | 10.8 | 486 | 0.6693 | 0.6473 | 0.6693 | 0.8181 |
|
| 295 |
+
| No log | 10.8444 | 488 | 0.6741 | 0.5726 | 0.6741 | 0.8210 |
|
| 296 |
+
| No log | 10.8889 | 490 | 0.7193 | 0.5835 | 0.7193 | 0.8481 |
|
| 297 |
+
| No log | 10.9333 | 492 | 0.6954 | 0.5759 | 0.6954 | 0.8339 |
|
| 298 |
+
| No log | 10.9778 | 494 | 0.6540 | 0.5523 | 0.6540 | 0.8087 |
|
| 299 |
+
| No log | 11.0222 | 496 | 0.6833 | 0.5446 | 0.6833 | 0.8266 |
|
| 300 |
+
| No log | 11.0667 | 498 | 0.8207 | 0.6097 | 0.8207 | 0.9059 |
|
| 301 |
+
| 0.254 | 11.1111 | 500 | 0.8770 | 0.6047 | 0.8770 | 0.9365 |
|
| 302 |
+
| 0.254 | 11.1556 | 502 | 0.7990 | 0.5944 | 0.7990 | 0.8939 |
|
| 303 |
+
| 0.254 | 11.2 | 504 | 0.6961 | 0.6237 | 0.6961 | 0.8343 |
|
| 304 |
+
| 0.254 | 11.2444 | 506 | 0.6564 | 0.5735 | 0.6564 | 0.8102 |
|
| 305 |
+
| 0.254 | 11.2889 | 508 | 0.6752 | 0.5071 | 0.6752 | 0.8217 |
|
| 306 |
+
| 0.254 | 11.3333 | 510 | 0.6834 | 0.4963 | 0.6834 | 0.8267 |
|
| 307 |
+
| 0.254 | 11.3778 | 512 | 0.6623 | 0.5735 | 0.6623 | 0.8138 |
|
| 308 |
+
| 0.254 | 11.4222 | 514 | 0.6483 | 0.5845 | 0.6483 | 0.8052 |
|
| 309 |
+
|
| 310 |
+
|
| 311 |
+
### Framework versions
|
| 312 |
+
|
| 313 |
+
- Transformers 4.44.2
|
| 314 |
+
- Pytorch 2.4.0+cu118
|
| 315 |
+
- Datasets 2.21.0
|
| 316 |
+
- 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:d6c1ba4aaf35be9af470f1e08a1f8a9446aee3380caa79e5d4ccc5d5d8e43711
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32a65074af0de290c5769cd245f0124415d14c513fbf1bdf805659cf97f3add7
|
| 3 |
+
size 5304
|