Training in progress, step 500
Browse files- README.md +330 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k7_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_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k7_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: 0.7187
|
| 19 |
+
- Qwk: 0.3341
|
| 20 |
+
- Mse: 0.7187
|
| 21 |
+
- Rmse: 0.8478
|
| 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 | 0.1176 | 2 | 2.5757 | -0.0924 | 2.5757 | 1.6049 |
|
| 53 |
+
| No log | 0.2353 | 4 | 1.3587 | 0.0994 | 1.3587 | 1.1656 |
|
| 54 |
+
| No log | 0.3529 | 6 | 1.1844 | -0.2292 | 1.1844 | 1.0883 |
|
| 55 |
+
| No log | 0.4706 | 8 | 0.9977 | -0.0426 | 0.9977 | 0.9988 |
|
| 56 |
+
| No log | 0.5882 | 10 | 0.9364 | 0.1007 | 0.9364 | 0.9677 |
|
| 57 |
+
| No log | 0.7059 | 12 | 0.8715 | 0.1648 | 0.8715 | 0.9335 |
|
| 58 |
+
| No log | 0.8235 | 14 | 0.8307 | -0.0103 | 0.8307 | 0.9114 |
|
| 59 |
+
| No log | 0.9412 | 16 | 0.8269 | -0.0483 | 0.8269 | 0.9094 |
|
| 60 |
+
| No log | 1.0588 | 18 | 0.9257 | 0.0495 | 0.9257 | 0.9621 |
|
| 61 |
+
| No log | 1.1765 | 20 | 0.9539 | -0.0700 | 0.9539 | 0.9767 |
|
| 62 |
+
| No log | 1.2941 | 22 | 0.8720 | 0.0027 | 0.8720 | 0.9338 |
|
| 63 |
+
| No log | 1.4118 | 24 | 0.8314 | 0.0 | 0.8314 | 0.9118 |
|
| 64 |
+
| No log | 1.5294 | 26 | 0.8248 | 0.0 | 0.8248 | 0.9082 |
|
| 65 |
+
| No log | 1.6471 | 28 | 0.8307 | 0.1236 | 0.8307 | 0.9114 |
|
| 66 |
+
| No log | 1.7647 | 30 | 0.7798 | 0.0 | 0.7798 | 0.8831 |
|
| 67 |
+
| No log | 1.8824 | 32 | 0.7549 | 0.0 | 0.7549 | 0.8688 |
|
| 68 |
+
| No log | 2.0 | 34 | 0.7683 | 0.0 | 0.7683 | 0.8765 |
|
| 69 |
+
| No log | 2.1176 | 36 | 0.8061 | 0.0481 | 0.8061 | 0.8978 |
|
| 70 |
+
| No log | 2.2353 | 38 | 0.9177 | 0.2526 | 0.9177 | 0.9579 |
|
| 71 |
+
| No log | 2.3529 | 40 | 0.9241 | 0.3444 | 0.9241 | 0.9613 |
|
| 72 |
+
| No log | 2.4706 | 42 | 0.8782 | 0.3173 | 0.8782 | 0.9371 |
|
| 73 |
+
| No log | 2.5882 | 44 | 0.7992 | 0.1372 | 0.7992 | 0.8940 |
|
| 74 |
+
| No log | 2.7059 | 46 | 0.7477 | 0.0937 | 0.7477 | 0.8647 |
|
| 75 |
+
| No log | 2.8235 | 48 | 0.7057 | 0.0428 | 0.7057 | 0.8400 |
|
| 76 |
+
| No log | 2.9412 | 50 | 0.7487 | 0.3243 | 0.7487 | 0.8653 |
|
| 77 |
+
| No log | 3.0588 | 52 | 0.8144 | 0.1648 | 0.8144 | 0.9025 |
|
| 78 |
+
| No log | 3.1765 | 54 | 0.8334 | 0.1699 | 0.8334 | 0.9129 |
|
| 79 |
+
| No log | 3.2941 | 56 | 0.8386 | 0.1094 | 0.8386 | 0.9157 |
|
| 80 |
+
| No log | 3.4118 | 58 | 0.8747 | -0.0027 | 0.8747 | 0.9353 |
|
| 81 |
+
| No log | 3.5294 | 60 | 0.9345 | -0.1275 | 0.9345 | 0.9667 |
|
| 82 |
+
| No log | 3.6471 | 62 | 0.8860 | -0.0444 | 0.8860 | 0.9413 |
|
| 83 |
+
| No log | 3.7647 | 64 | 0.7937 | 0.0 | 0.7937 | 0.8909 |
|
| 84 |
+
| No log | 3.8824 | 66 | 0.7158 | 0.0889 | 0.7158 | 0.8460 |
|
| 85 |
+
| No log | 4.0 | 68 | 0.7009 | 0.0393 | 0.7009 | 0.8372 |
|
| 86 |
+
| No log | 4.1176 | 70 | 0.7320 | 0.0359 | 0.7320 | 0.8556 |
|
| 87 |
+
| No log | 4.2353 | 72 | 0.7952 | -0.0051 | 0.7952 | 0.8917 |
|
| 88 |
+
| No log | 4.3529 | 74 | 0.8104 | 0.0265 | 0.8104 | 0.9002 |
|
| 89 |
+
| No log | 4.4706 | 76 | 0.8378 | 0.0927 | 0.8378 | 0.9153 |
|
| 90 |
+
| No log | 4.5882 | 78 | 0.8915 | 0.0966 | 0.8915 | 0.9442 |
|
| 91 |
+
| No log | 4.7059 | 80 | 0.9184 | 0.1699 | 0.9184 | 0.9583 |
|
| 92 |
+
| No log | 4.8235 | 82 | 0.9273 | 0.2171 | 0.9273 | 0.9630 |
|
| 93 |
+
| No log | 4.9412 | 84 | 0.9053 | 0.1972 | 0.9053 | 0.9515 |
|
| 94 |
+
| No log | 5.0588 | 86 | 0.9132 | 0.0245 | 0.9132 | 0.9556 |
|
| 95 |
+
| No log | 5.1765 | 88 | 0.8966 | 0.0968 | 0.8966 | 0.9469 |
|
| 96 |
+
| No log | 5.2941 | 90 | 0.9317 | 0.1303 | 0.9317 | 0.9652 |
|
| 97 |
+
| No log | 5.4118 | 92 | 0.9620 | 0.2063 | 0.9620 | 0.9808 |
|
| 98 |
+
| No log | 5.5294 | 94 | 0.9345 | 0.2632 | 0.9345 | 0.9667 |
|
| 99 |
+
| No log | 5.6471 | 96 | 0.8433 | 0.3238 | 0.8433 | 0.9183 |
|
| 100 |
+
| No log | 5.7647 | 98 | 0.8240 | 0.2007 | 0.8240 | 0.9078 |
|
| 101 |
+
| No log | 5.8824 | 100 | 0.8275 | -0.0070 | 0.8275 | 0.9096 |
|
| 102 |
+
| No log | 6.0 | 102 | 0.8620 | 0.0362 | 0.8620 | 0.9284 |
|
| 103 |
+
| No log | 6.1176 | 104 | 0.8316 | 0.0697 | 0.8316 | 0.9119 |
|
| 104 |
+
| No log | 6.2353 | 106 | 0.8263 | 0.2345 | 0.8263 | 0.9090 |
|
| 105 |
+
| No log | 6.3529 | 108 | 0.8755 | 0.2604 | 0.8755 | 0.9357 |
|
| 106 |
+
| No log | 6.4706 | 110 | 0.8392 | 0.2171 | 0.8392 | 0.9161 |
|
| 107 |
+
| No log | 6.5882 | 112 | 0.8389 | 0.2063 | 0.8389 | 0.9159 |
|
| 108 |
+
| No log | 6.7059 | 114 | 0.8407 | 0.0 | 0.8407 | 0.9169 |
|
| 109 |
+
| No log | 6.8235 | 116 | 0.7234 | 0.1829 | 0.7234 | 0.8505 |
|
| 110 |
+
| No log | 6.9412 | 118 | 0.6556 | 0.2819 | 0.6556 | 0.8097 |
|
| 111 |
+
| No log | 7.0588 | 120 | 0.6881 | 0.3950 | 0.6881 | 0.8295 |
|
| 112 |
+
| No log | 7.1765 | 122 | 0.8563 | 0.3499 | 0.8563 | 0.9254 |
|
| 113 |
+
| No log | 7.2941 | 124 | 0.9866 | 0.2921 | 0.9866 | 0.9933 |
|
| 114 |
+
| No log | 7.4118 | 126 | 0.9981 | 0.2464 | 0.9981 | 0.9991 |
|
| 115 |
+
| No log | 7.5294 | 128 | 1.0640 | 0.1354 | 1.0640 | 1.0315 |
|
| 116 |
+
| No log | 7.6471 | 130 | 1.5347 | 0.1007 | 1.5347 | 1.2388 |
|
| 117 |
+
| No log | 7.7647 | 132 | 1.5733 | 0.0790 | 1.5733 | 1.2543 |
|
| 118 |
+
| No log | 7.8824 | 134 | 1.2396 | 0.1332 | 1.2396 | 1.1134 |
|
| 119 |
+
| No log | 8.0 | 136 | 0.9817 | 0.0801 | 0.9817 | 0.9908 |
|
| 120 |
+
| No log | 8.1176 | 138 | 0.9364 | 0.2832 | 0.9364 | 0.9677 |
|
| 121 |
+
| No log | 8.2353 | 140 | 0.8926 | 0.3183 | 0.8926 | 0.9448 |
|
| 122 |
+
| No log | 8.3529 | 142 | 0.8516 | 0.3221 | 0.8516 | 0.9228 |
|
| 123 |
+
| No log | 8.4706 | 144 | 0.8222 | 0.2414 | 0.8222 | 0.9068 |
|
| 124 |
+
| No log | 8.5882 | 146 | 0.8010 | 0.2813 | 0.8010 | 0.8950 |
|
| 125 |
+
| No log | 8.7059 | 148 | 0.7963 | 0.2784 | 0.7963 | 0.8924 |
|
| 126 |
+
| No log | 8.8235 | 150 | 0.8079 | 0.3372 | 0.8079 | 0.8989 |
|
| 127 |
+
| No log | 8.9412 | 152 | 0.8412 | 0.3699 | 0.8412 | 0.9171 |
|
| 128 |
+
| No log | 9.0588 | 154 | 0.7978 | 0.3637 | 0.7978 | 0.8932 |
|
| 129 |
+
| No log | 9.1765 | 156 | 0.7614 | 0.3099 | 0.7614 | 0.8726 |
|
| 130 |
+
| No log | 9.2941 | 158 | 0.7245 | 0.1699 | 0.7245 | 0.8512 |
|
| 131 |
+
| No log | 9.4118 | 160 | 0.7185 | 0.1807 | 0.7185 | 0.8477 |
|
| 132 |
+
| No log | 9.5294 | 162 | 0.7381 | 0.1268 | 0.7381 | 0.8592 |
|
| 133 |
+
| No log | 9.6471 | 164 | 0.7843 | 0.2171 | 0.7843 | 0.8856 |
|
| 134 |
+
| No log | 9.7647 | 166 | 0.8367 | 0.2328 | 0.8367 | 0.9147 |
|
| 135 |
+
| No log | 9.8824 | 168 | 0.8363 | 0.1995 | 0.8363 | 0.9145 |
|
| 136 |
+
| No log | 10.0 | 170 | 0.8047 | 0.2589 | 0.8047 | 0.8970 |
|
| 137 |
+
| No log | 10.1176 | 172 | 0.8180 | 0.0652 | 0.8180 | 0.9044 |
|
| 138 |
+
| No log | 10.2353 | 174 | 0.8233 | 0.0652 | 0.8233 | 0.9074 |
|
| 139 |
+
| No log | 10.3529 | 176 | 0.7997 | 0.2027 | 0.7997 | 0.8942 |
|
| 140 |
+
| No log | 10.4706 | 178 | 0.8016 | 0.3372 | 0.8016 | 0.8953 |
|
| 141 |
+
| No log | 10.5882 | 180 | 0.7845 | 0.3819 | 0.7845 | 0.8857 |
|
| 142 |
+
| No log | 10.7059 | 182 | 0.6968 | 0.3032 | 0.6968 | 0.8347 |
|
| 143 |
+
| No log | 10.8235 | 184 | 0.6736 | 0.3425 | 0.6736 | 0.8208 |
|
| 144 |
+
| No log | 10.9412 | 186 | 0.7071 | 0.3127 | 0.7071 | 0.8409 |
|
| 145 |
+
| No log | 11.0588 | 188 | 0.7794 | 0.3372 | 0.7794 | 0.8828 |
|
| 146 |
+
| No log | 11.1765 | 190 | 0.8896 | 0.3782 | 0.8896 | 0.9432 |
|
| 147 |
+
| No log | 11.2941 | 192 | 0.8603 | 0.4251 | 0.8603 | 0.9275 |
|
| 148 |
+
| No log | 11.4118 | 194 | 0.7622 | 0.2784 | 0.7622 | 0.8730 |
|
| 149 |
+
| No log | 11.5294 | 196 | 0.7462 | 0.2683 | 0.7462 | 0.8638 |
|
| 150 |
+
| No log | 11.6471 | 198 | 0.7544 | 0.2683 | 0.7544 | 0.8686 |
|
| 151 |
+
| No log | 11.7647 | 200 | 0.7524 | 0.2319 | 0.7524 | 0.8674 |
|
| 152 |
+
| No log | 11.8824 | 202 | 0.8204 | 0.4089 | 0.8204 | 0.9058 |
|
| 153 |
+
| No log | 12.0 | 204 | 0.8332 | 0.3590 | 0.8332 | 0.9128 |
|
| 154 |
+
| No log | 12.1176 | 206 | 0.8053 | 0.1264 | 0.8053 | 0.8974 |
|
| 155 |
+
| No log | 12.2353 | 208 | 0.8030 | 0.2043 | 0.8030 | 0.8961 |
|
| 156 |
+
| No log | 12.3529 | 210 | 0.8035 | 0.1051 | 0.8035 | 0.8964 |
|
| 157 |
+
| No log | 12.4706 | 212 | 0.7790 | 0.2158 | 0.7790 | 0.8826 |
|
| 158 |
+
| No log | 12.5882 | 214 | 0.7441 | 0.2319 | 0.7441 | 0.8626 |
|
| 159 |
+
| No log | 12.7059 | 216 | 0.7776 | 0.3894 | 0.7776 | 0.8818 |
|
| 160 |
+
| No log | 12.8235 | 218 | 0.7996 | 0.4014 | 0.7996 | 0.8942 |
|
| 161 |
+
| No log | 12.9412 | 220 | 0.7439 | 0.4052 | 0.7439 | 0.8625 |
|
| 162 |
+
| No log | 13.0588 | 222 | 0.7111 | 0.3471 | 0.7111 | 0.8433 |
|
| 163 |
+
| No log | 13.1765 | 224 | 0.6985 | 0.3341 | 0.6985 | 0.8357 |
|
| 164 |
+
| No log | 13.2941 | 226 | 0.7284 | 0.3545 | 0.7284 | 0.8535 |
|
| 165 |
+
| No log | 13.4118 | 228 | 0.8148 | 0.3372 | 0.8148 | 0.9027 |
|
| 166 |
+
| No log | 13.5294 | 230 | 0.9035 | 0.3519 | 0.9035 | 0.9505 |
|
| 167 |
+
| No log | 13.6471 | 232 | 0.8974 | 0.2754 | 0.8974 | 0.9473 |
|
| 168 |
+
| No log | 13.7647 | 234 | 0.8592 | 0.2847 | 0.8592 | 0.9269 |
|
| 169 |
+
| No log | 13.8824 | 236 | 0.8327 | 0.3737 | 0.8327 | 0.9125 |
|
| 170 |
+
| No log | 14.0 | 238 | 0.8219 | 0.3918 | 0.8219 | 0.9066 |
|
| 171 |
+
| No log | 14.1176 | 240 | 0.7738 | 0.3032 | 0.7738 | 0.8797 |
|
| 172 |
+
| No log | 14.2353 | 242 | 0.7455 | 0.3712 | 0.7455 | 0.8634 |
|
| 173 |
+
| No log | 14.3529 | 244 | 0.7875 | 0.3302 | 0.7875 | 0.8874 |
|
| 174 |
+
| No log | 14.4706 | 246 | 0.8593 | 0.3869 | 0.8593 | 0.9270 |
|
| 175 |
+
| No log | 14.5882 | 248 | 0.9272 | 0.3825 | 0.9272 | 0.9629 |
|
| 176 |
+
| No log | 14.7059 | 250 | 0.8637 | 0.3538 | 0.8637 | 0.9294 |
|
| 177 |
+
| No log | 14.8235 | 252 | 0.7736 | 0.3894 | 0.7736 | 0.8795 |
|
| 178 |
+
| No log | 14.9412 | 254 | 0.7035 | 0.3594 | 0.7035 | 0.8387 |
|
| 179 |
+
| No log | 15.0588 | 256 | 0.6780 | 0.4001 | 0.6780 | 0.8234 |
|
| 180 |
+
| No log | 15.1765 | 258 | 0.6778 | 0.4291 | 0.6778 | 0.8233 |
|
| 181 |
+
| No log | 15.2941 | 260 | 0.6805 | 0.4001 | 0.6805 | 0.8249 |
|
| 182 |
+
| No log | 15.4118 | 262 | 0.7081 | 0.4158 | 0.7081 | 0.8415 |
|
| 183 |
+
| No log | 15.5294 | 264 | 0.7434 | 0.3868 | 0.7434 | 0.8622 |
|
| 184 |
+
| No log | 15.6471 | 266 | 0.8074 | 0.3746 | 0.8074 | 0.8986 |
|
| 185 |
+
| No log | 15.7647 | 268 | 0.8077 | 0.3699 | 0.8077 | 0.8987 |
|
| 186 |
+
| No log | 15.8824 | 270 | 0.8001 | 0.4014 | 0.8001 | 0.8945 |
|
| 187 |
+
| No log | 16.0 | 272 | 0.7637 | 0.3770 | 0.7637 | 0.8739 |
|
| 188 |
+
| No log | 16.1176 | 274 | 0.7132 | 0.3518 | 0.7132 | 0.8445 |
|
| 189 |
+
| No log | 16.2353 | 276 | 0.7116 | 0.3238 | 0.7116 | 0.8436 |
|
| 190 |
+
| No log | 16.3529 | 278 | 0.7267 | 0.3238 | 0.7267 | 0.8525 |
|
| 191 |
+
| No log | 16.4706 | 280 | 0.7366 | 0.3099 | 0.7366 | 0.8583 |
|
| 192 |
+
| No log | 16.5882 | 282 | 0.7447 | 0.3712 | 0.7447 | 0.8630 |
|
| 193 |
+
| No log | 16.7059 | 284 | 0.7767 | 0.3712 | 0.7767 | 0.8813 |
|
| 194 |
+
| No log | 16.8235 | 286 | 0.8651 | 0.3675 | 0.8651 | 0.9301 |
|
| 195 |
+
| No log | 16.9412 | 288 | 0.8676 | 0.3606 | 0.8676 | 0.9315 |
|
| 196 |
+
| No log | 17.0588 | 290 | 0.8148 | 0.3819 | 0.8148 | 0.9027 |
|
| 197 |
+
| No log | 17.1765 | 292 | 0.8137 | 0.3637 | 0.8137 | 0.9021 |
|
| 198 |
+
| No log | 17.2941 | 294 | 0.7826 | 0.3737 | 0.7826 | 0.8847 |
|
| 199 |
+
| No log | 17.4118 | 296 | 0.7781 | 0.2847 | 0.7781 | 0.8821 |
|
| 200 |
+
| No log | 17.5294 | 298 | 0.7970 | 0.2319 | 0.7970 | 0.8927 |
|
| 201 |
+
| No log | 17.6471 | 300 | 0.8518 | 0.1918 | 0.8518 | 0.9230 |
|
| 202 |
+
| No log | 17.7647 | 302 | 0.9251 | 0.1866 | 0.9251 | 0.9618 |
|
| 203 |
+
| No log | 17.8824 | 304 | 0.9407 | 0.1866 | 0.9407 | 0.9699 |
|
| 204 |
+
| No log | 18.0 | 306 | 0.8990 | 0.1918 | 0.8990 | 0.9482 |
|
| 205 |
+
| No log | 18.1176 | 308 | 0.8168 | 0.2847 | 0.8168 | 0.9038 |
|
| 206 |
+
| No log | 18.2353 | 310 | 0.7374 | 0.3919 | 0.7374 | 0.8587 |
|
| 207 |
+
| No log | 18.3529 | 312 | 0.7206 | 0.3919 | 0.7206 | 0.8489 |
|
| 208 |
+
| No log | 18.4706 | 314 | 0.7563 | 0.4684 | 0.7563 | 0.8696 |
|
| 209 |
+
| No log | 18.5882 | 316 | 0.7759 | 0.4684 | 0.7759 | 0.8809 |
|
| 210 |
+
| No log | 18.7059 | 318 | 0.7929 | 0.4684 | 0.7929 | 0.8905 |
|
| 211 |
+
| No log | 18.8235 | 320 | 0.7879 | 0.3572 | 0.7879 | 0.8876 |
|
| 212 |
+
| No log | 18.9412 | 322 | 0.7850 | 0.3572 | 0.7850 | 0.8860 |
|
| 213 |
+
| No log | 19.0588 | 324 | 0.7964 | 0.4270 | 0.7964 | 0.8924 |
|
| 214 |
+
| No log | 19.1765 | 326 | 0.8016 | 0.3996 | 0.8016 | 0.8953 |
|
| 215 |
+
| No log | 19.2941 | 328 | 0.8174 | 0.3590 | 0.8174 | 0.9041 |
|
| 216 |
+
| No log | 19.4118 | 330 | 0.7876 | 0.4247 | 0.7876 | 0.8874 |
|
| 217 |
+
| No log | 19.5294 | 332 | 0.8040 | 0.3770 | 0.8040 | 0.8966 |
|
| 218 |
+
| No log | 19.6471 | 334 | 0.7851 | 0.3770 | 0.7851 | 0.8861 |
|
| 219 |
+
| No log | 19.7647 | 336 | 0.7121 | 0.4592 | 0.7121 | 0.8439 |
|
| 220 |
+
| No log | 19.8824 | 338 | 0.6655 | 0.2819 | 0.6655 | 0.8158 |
|
| 221 |
+
| No log | 20.0 | 340 | 0.6671 | 0.2819 | 0.6671 | 0.8167 |
|
| 222 |
+
| No log | 20.1176 | 342 | 0.6997 | 0.3782 | 0.6997 | 0.8365 |
|
| 223 |
+
| No log | 20.2353 | 344 | 0.7596 | 0.4076 | 0.7596 | 0.8715 |
|
| 224 |
+
| No log | 20.3529 | 346 | 0.8016 | 0.3372 | 0.8016 | 0.8953 |
|
| 225 |
+
| No log | 20.4706 | 348 | 0.8415 | 0.3372 | 0.8415 | 0.9173 |
|
| 226 |
+
| No log | 20.5882 | 350 | 0.8207 | 0.3519 | 0.8207 | 0.9059 |
|
| 227 |
+
| No log | 20.7059 | 352 | 0.8039 | 0.3519 | 0.8039 | 0.8966 |
|
| 228 |
+
| No log | 20.8235 | 354 | 0.7602 | 0.3544 | 0.7602 | 0.8719 |
|
| 229 |
+
| No log | 20.9412 | 356 | 0.7442 | 0.4190 | 0.7442 | 0.8626 |
|
| 230 |
+
| No log | 21.0588 | 358 | 0.7384 | 0.4167 | 0.7384 | 0.8593 |
|
| 231 |
+
| No log | 21.1765 | 360 | 0.7168 | 0.4479 | 0.7168 | 0.8467 |
|
| 232 |
+
| No log | 21.2941 | 362 | 0.7191 | 0.4479 | 0.7191 | 0.8480 |
|
| 233 |
+
| No log | 21.4118 | 364 | 0.7384 | 0.4576 | 0.7384 | 0.8593 |
|
| 234 |
+
| No log | 21.5294 | 366 | 0.7592 | 0.4167 | 0.7592 | 0.8713 |
|
| 235 |
+
| No log | 21.6471 | 368 | 0.7503 | 0.4576 | 0.7503 | 0.8662 |
|
| 236 |
+
| No log | 21.7647 | 370 | 0.7116 | 0.4576 | 0.7116 | 0.8436 |
|
| 237 |
+
| No log | 21.8824 | 372 | 0.6735 | 0.3755 | 0.6735 | 0.8207 |
|
| 238 |
+
| No log | 22.0 | 374 | 0.6573 | 0.3123 | 0.6573 | 0.8107 |
|
| 239 |
+
| No log | 22.1176 | 376 | 0.6633 | 0.3976 | 0.6633 | 0.8144 |
|
| 240 |
+
| No log | 22.2353 | 378 | 0.7019 | 0.4753 | 0.7019 | 0.8378 |
|
| 241 |
+
| No log | 22.3529 | 380 | 0.7806 | 0.4167 | 0.7806 | 0.8835 |
|
| 242 |
+
| No log | 22.4706 | 382 | 0.9162 | 0.3913 | 0.9162 | 0.9572 |
|
| 243 |
+
| No log | 22.5882 | 384 | 0.9838 | 0.3128 | 0.9838 | 0.9919 |
|
| 244 |
+
| No log | 22.7059 | 386 | 0.9348 | 0.3012 | 0.9348 | 0.9668 |
|
| 245 |
+
| No log | 22.8235 | 388 | 0.8444 | 0.2883 | 0.8444 | 0.9189 |
|
| 246 |
+
| No log | 22.9412 | 390 | 0.7869 | 0.2145 | 0.7869 | 0.8871 |
|
| 247 |
+
| No log | 23.0588 | 392 | 0.7715 | 0.1863 | 0.7715 | 0.8783 |
|
| 248 |
+
| No log | 23.1765 | 394 | 0.7584 | 0.2206 | 0.7584 | 0.8709 |
|
| 249 |
+
| No log | 23.2941 | 396 | 0.7867 | 0.3020 | 0.7867 | 0.8870 |
|
| 250 |
+
| No log | 23.4118 | 398 | 0.8898 | 0.3972 | 0.8898 | 0.9433 |
|
| 251 |
+
| No log | 23.5294 | 400 | 0.9919 | 0.3473 | 0.9919 | 0.9960 |
|
| 252 |
+
| No log | 23.6471 | 402 | 1.0320 | 0.2781 | 1.0320 | 1.0159 |
|
| 253 |
+
| No log | 23.7647 | 404 | 1.0073 | 0.2387 | 1.0073 | 1.0036 |
|
| 254 |
+
| No log | 23.8824 | 406 | 0.9323 | 0.3060 | 0.9323 | 0.9656 |
|
| 255 |
+
| No log | 24.0 | 408 | 0.9247 | 0.2532 | 0.9247 | 0.9616 |
|
| 256 |
+
| No log | 24.1176 | 410 | 0.9271 | 0.2838 | 0.9271 | 0.9629 |
|
| 257 |
+
| No log | 24.2353 | 412 | 0.9283 | 0.3106 | 0.9283 | 0.9635 |
|
| 258 |
+
| No log | 24.3529 | 414 | 0.9059 | 0.2813 | 0.9059 | 0.9518 |
|
| 259 |
+
| No log | 24.4706 | 416 | 0.9277 | 0.3344 | 0.9277 | 0.9632 |
|
| 260 |
+
| No log | 24.5882 | 418 | 0.9200 | 0.3918 | 0.9200 | 0.9591 |
|
| 261 |
+
| No log | 24.7059 | 420 | 0.8989 | 0.3991 | 0.8989 | 0.9481 |
|
| 262 |
+
| No log | 24.8235 | 422 | 0.8600 | 0.3894 | 0.8600 | 0.9274 |
|
| 263 |
+
| No log | 24.9412 | 424 | 0.8149 | 0.4392 | 0.8149 | 0.9027 |
|
| 264 |
+
| No log | 25.0588 | 426 | 0.7731 | 0.4243 | 0.7731 | 0.8793 |
|
| 265 |
+
| No log | 25.1765 | 428 | 0.7624 | 0.3976 | 0.7624 | 0.8731 |
|
| 266 |
+
| No log | 25.2941 | 430 | 0.7936 | 0.4243 | 0.7936 | 0.8909 |
|
| 267 |
+
| No log | 25.4118 | 432 | 0.8036 | 0.3622 | 0.8036 | 0.8964 |
|
| 268 |
+
| No log | 25.5294 | 434 | 0.8172 | 0.3224 | 0.8172 | 0.9040 |
|
| 269 |
+
| No log | 25.6471 | 436 | 0.7936 | 0.3224 | 0.7936 | 0.8908 |
|
| 270 |
+
| No log | 25.7647 | 438 | 0.7833 | 0.3498 | 0.7833 | 0.8851 |
|
| 271 |
+
| No log | 25.8824 | 440 | 0.7797 | 0.4663 | 0.7797 | 0.8830 |
|
| 272 |
+
| No log | 26.0 | 442 | 0.8268 | 0.3843 | 0.8268 | 0.9093 |
|
| 273 |
+
| No log | 26.1176 | 444 | 0.8310 | 0.3843 | 0.8310 | 0.9116 |
|
| 274 |
+
| No log | 26.2353 | 446 | 0.7962 | 0.4753 | 0.7962 | 0.8923 |
|
| 275 |
+
| No log | 26.3529 | 448 | 0.7693 | 0.4753 | 0.7693 | 0.8771 |
|
| 276 |
+
| No log | 26.4706 | 450 | 0.7771 | 0.4479 | 0.7771 | 0.8816 |
|
| 277 |
+
| No log | 26.5882 | 452 | 0.8233 | 0.4052 | 0.8233 | 0.9074 |
|
| 278 |
+
| No log | 26.7059 | 454 | 0.8303 | 0.3637 | 0.8303 | 0.9112 |
|
| 279 |
+
| No log | 26.8235 | 456 | 0.7922 | 0.4479 | 0.7922 | 0.8901 |
|
| 280 |
+
| No log | 26.9412 | 458 | 0.7423 | 0.3622 | 0.7423 | 0.8616 |
|
| 281 |
+
| No log | 27.0588 | 460 | 0.7357 | 0.2981 | 0.7357 | 0.8577 |
|
| 282 |
+
| No log | 27.1765 | 462 | 0.7645 | 0.3594 | 0.7645 | 0.8744 |
|
| 283 |
+
| No log | 27.2941 | 464 | 0.8427 | 0.3972 | 0.8427 | 0.9180 |
|
| 284 |
+
| No log | 27.4118 | 466 | 0.9057 | 0.3675 | 0.9057 | 0.9517 |
|
| 285 |
+
| No log | 27.5294 | 468 | 0.9028 | 0.3675 | 0.9028 | 0.9501 |
|
| 286 |
+
| No log | 27.6471 | 470 | 0.8554 | 0.3894 | 0.8554 | 0.9249 |
|
| 287 |
+
| No log | 27.7647 | 472 | 0.8067 | 0.4247 | 0.8067 | 0.8982 |
|
| 288 |
+
| No log | 27.8824 | 474 | 0.8030 | 0.4247 | 0.8030 | 0.8961 |
|
| 289 |
+
| No log | 28.0 | 476 | 0.7978 | 0.4247 | 0.7978 | 0.8932 |
|
| 290 |
+
| No log | 28.1176 | 478 | 0.8022 | 0.4052 | 0.8022 | 0.8957 |
|
| 291 |
+
| No log | 28.2353 | 480 | 0.8193 | 0.3972 | 0.8193 | 0.9051 |
|
| 292 |
+
| No log | 28.3529 | 482 | 0.8121 | 0.4479 | 0.8121 | 0.9012 |
|
| 293 |
+
| No log | 28.4706 | 484 | 0.8070 | 0.4479 | 0.8070 | 0.8984 |
|
| 294 |
+
| No log | 28.5882 | 486 | 0.7850 | 0.4219 | 0.7850 | 0.8860 |
|
| 295 |
+
| No log | 28.7059 | 488 | 0.7744 | 0.4502 | 0.7744 | 0.8800 |
|
| 296 |
+
| No log | 28.8235 | 490 | 0.7633 | 0.4502 | 0.7633 | 0.8737 |
|
| 297 |
+
| No log | 28.9412 | 492 | 0.7753 | 0.4774 | 0.7753 | 0.8805 |
|
| 298 |
+
| No log | 29.0588 | 494 | 0.8084 | 0.4076 | 0.8084 | 0.8991 |
|
| 299 |
+
| No log | 29.1765 | 496 | 0.8381 | 0.4330 | 0.8381 | 0.9155 |
|
| 300 |
+
| No log | 29.2941 | 498 | 0.8586 | 0.4409 | 0.8586 | 0.9266 |
|
| 301 |
+
| 0.3134 | 29.4118 | 500 | 0.8490 | 0.4224 | 0.8490 | 0.9214 |
|
| 302 |
+
| 0.3134 | 29.5294 | 502 | 0.8322 | 0.3972 | 0.8322 | 0.9123 |
|
| 303 |
+
| 0.3134 | 29.6471 | 504 | 0.7995 | 0.4479 | 0.7995 | 0.8942 |
|
| 304 |
+
| 0.3134 | 29.7647 | 506 | 0.7992 | 0.4845 | 0.7992 | 0.8940 |
|
| 305 |
+
| 0.3134 | 29.8824 | 508 | 0.8180 | 0.4414 | 0.8180 | 0.9044 |
|
| 306 |
+
| 0.3134 | 30.0 | 510 | 0.8297 | 0.4414 | 0.8297 | 0.9109 |
|
| 307 |
+
| 0.3134 | 30.1176 | 512 | 0.8231 | 0.3649 | 0.8231 | 0.9072 |
|
| 308 |
+
| 0.3134 | 30.2353 | 514 | 0.8386 | 0.3737 | 0.8386 | 0.9158 |
|
| 309 |
+
| 0.3134 | 30.3529 | 516 | 0.8447 | 0.3737 | 0.8447 | 0.9191 |
|
| 310 |
+
| 0.3134 | 30.4706 | 518 | 0.8344 | 0.3471 | 0.8344 | 0.9135 |
|
| 311 |
+
| 0.3134 | 30.5882 | 520 | 0.7964 | 0.4330 | 0.7964 | 0.8924 |
|
| 312 |
+
| 0.3134 | 30.7059 | 522 | 0.7581 | 0.3782 | 0.7581 | 0.8707 |
|
| 313 |
+
| 0.3134 | 30.8235 | 524 | 0.7483 | 0.3782 | 0.7483 | 0.8651 |
|
| 314 |
+
| 0.3134 | 30.9412 | 526 | 0.7706 | 0.4414 | 0.7706 | 0.8779 |
|
| 315 |
+
| 0.3134 | 31.0588 | 528 | 0.8221 | 0.3972 | 0.8221 | 0.9067 |
|
| 316 |
+
| 0.3134 | 31.1765 | 530 | 0.8522 | 0.3972 | 0.8522 | 0.9231 |
|
| 317 |
+
| 0.3134 | 31.2941 | 532 | 0.8332 | 0.4392 | 0.8332 | 0.9128 |
|
| 318 |
+
| 0.3134 | 31.4118 | 534 | 0.7971 | 0.4219 | 0.7971 | 0.8928 |
|
| 319 |
+
| 0.3134 | 31.5294 | 536 | 0.7689 | 0.3950 | 0.7689 | 0.8768 |
|
| 320 |
+
| 0.3134 | 31.6471 | 538 | 0.7299 | 0.3976 | 0.7299 | 0.8543 |
|
| 321 |
+
| 0.3134 | 31.7647 | 540 | 0.7136 | 0.3976 | 0.7136 | 0.8447 |
|
| 322 |
+
| 0.3134 | 31.8824 | 542 | 0.7187 | 0.3341 | 0.7187 | 0.8478 |
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
### Framework versions
|
| 326 |
+
|
| 327 |
+
- Transformers 4.44.2
|
| 328 |
+
- Pytorch 2.4.0+cu118
|
| 329 |
+
- Datasets 2.21.0
|
| 330 |
+
- 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:db5fcb64dc3c9dcbf34e66a43928c1acb9d82654d58cbf05a037dc0c7766807e
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:813090c036c62e5b1ebb7b6aecede864b407ce8d7bb47f7e7817c381f65678f1
|
| 3 |
+
size 5368
|