Training in progress, step 500
Browse files- README.md +366 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_k16_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_k16_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: 0.6822
|
| 19 |
+
- Qwk: 0.5681
|
| 20 |
+
- Mse: 0.6822
|
| 21 |
+
- Rmse: 0.8260
|
| 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 | 0.025 | 2 | 3.7907 | -0.0215 | 3.7907 | 1.9470 |
|
| 53 |
+
| No log | 0.05 | 4 | 1.9917 | 0.1002 | 1.9917 | 1.4113 |
|
| 54 |
+
| No log | 0.075 | 6 | 1.6123 | 0.0733 | 1.6123 | 1.2698 |
|
| 55 |
+
| No log | 0.1 | 8 | 1.0585 | 0.2740 | 1.0585 | 1.0288 |
|
| 56 |
+
| No log | 0.125 | 10 | 1.0539 | 0.0762 | 1.0539 | 1.0266 |
|
| 57 |
+
| No log | 0.15 | 12 | 1.1270 | -0.0125 | 1.1270 | 1.0616 |
|
| 58 |
+
| No log | 0.175 | 14 | 1.1010 | 0.0762 | 1.1010 | 1.0493 |
|
| 59 |
+
| No log | 0.2 | 16 | 1.0050 | 0.2991 | 1.0050 | 1.0025 |
|
| 60 |
+
| No log | 0.225 | 18 | 1.5321 | 0.1004 | 1.5321 | 1.2378 |
|
| 61 |
+
| No log | 0.25 | 20 | 1.9570 | 0.2486 | 1.9570 | 1.3989 |
|
| 62 |
+
| No log | 0.275 | 22 | 1.7508 | 0.1744 | 1.7508 | 1.3232 |
|
| 63 |
+
| No log | 0.3 | 24 | 1.3354 | 0.0399 | 1.3354 | 1.1556 |
|
| 64 |
+
| No log | 0.325 | 26 | 1.0282 | 0.2561 | 1.0282 | 1.0140 |
|
| 65 |
+
| No log | 0.35 | 28 | 0.9671 | 0.4011 | 0.9671 | 0.9834 |
|
| 66 |
+
| No log | 0.375 | 30 | 0.9993 | 0.1954 | 0.9993 | 0.9996 |
|
| 67 |
+
| No log | 0.4 | 32 | 0.9862 | 0.1926 | 0.9862 | 0.9931 |
|
| 68 |
+
| No log | 0.425 | 34 | 0.9470 | 0.3153 | 0.9470 | 0.9731 |
|
| 69 |
+
| No log | 0.45 | 36 | 0.9876 | 0.3127 | 0.9876 | 0.9938 |
|
| 70 |
+
| No log | 0.475 | 38 | 1.0872 | 0.1764 | 1.0872 | 1.0427 |
|
| 71 |
+
| No log | 0.5 | 40 | 1.1064 | 0.1379 | 1.1064 | 1.0519 |
|
| 72 |
+
| No log | 0.525 | 42 | 1.1010 | 0.1764 | 1.1010 | 1.0493 |
|
| 73 |
+
| No log | 0.55 | 44 | 1.0796 | 0.2613 | 1.0796 | 1.0391 |
|
| 74 |
+
| No log | 0.575 | 46 | 0.9739 | 0.2777 | 0.9739 | 0.9869 |
|
| 75 |
+
| No log | 0.6 | 48 | 0.7995 | 0.4076 | 0.7995 | 0.8941 |
|
| 76 |
+
| No log | 0.625 | 50 | 0.7627 | 0.4845 | 0.7627 | 0.8733 |
|
| 77 |
+
| No log | 0.65 | 52 | 0.9086 | 0.3793 | 0.9086 | 0.9532 |
|
| 78 |
+
| No log | 0.675 | 54 | 1.1779 | 0.3633 | 1.1779 | 1.0853 |
|
| 79 |
+
| No log | 0.7 | 56 | 1.1284 | 0.3654 | 1.1284 | 1.0622 |
|
| 80 |
+
| No log | 0.725 | 58 | 0.8364 | 0.4671 | 0.8364 | 0.9145 |
|
| 81 |
+
| No log | 0.75 | 60 | 0.7111 | 0.6164 | 0.7111 | 0.8432 |
|
| 82 |
+
| No log | 0.775 | 62 | 0.7721 | 0.5353 | 0.7721 | 0.8787 |
|
| 83 |
+
| No log | 0.8 | 64 | 0.8052 | 0.5527 | 0.8052 | 0.8973 |
|
| 84 |
+
| No log | 0.825 | 66 | 0.8305 | 0.5114 | 0.8305 | 0.9113 |
|
| 85 |
+
| No log | 0.85 | 68 | 0.7102 | 0.5832 | 0.7102 | 0.8427 |
|
| 86 |
+
| No log | 0.875 | 70 | 0.7389 | 0.5717 | 0.7389 | 0.8596 |
|
| 87 |
+
| No log | 0.9 | 72 | 0.7906 | 0.5667 | 0.7906 | 0.8891 |
|
| 88 |
+
| No log | 0.925 | 74 | 0.7206 | 0.6427 | 0.7206 | 0.8489 |
|
| 89 |
+
| No log | 0.95 | 76 | 0.6354 | 0.6207 | 0.6354 | 0.7971 |
|
| 90 |
+
| No log | 0.975 | 78 | 0.6552 | 0.5404 | 0.6552 | 0.8094 |
|
| 91 |
+
| No log | 1.0 | 80 | 0.6491 | 0.5933 | 0.6491 | 0.8057 |
|
| 92 |
+
| No log | 1.025 | 82 | 0.6423 | 0.6187 | 0.6423 | 0.8014 |
|
| 93 |
+
| No log | 1.05 | 84 | 0.6568 | 0.6143 | 0.6568 | 0.8105 |
|
| 94 |
+
| No log | 1.075 | 86 | 0.6614 | 0.6167 | 0.6614 | 0.8133 |
|
| 95 |
+
| No log | 1.1 | 88 | 0.6748 | 0.6167 | 0.6748 | 0.8214 |
|
| 96 |
+
| No log | 1.125 | 90 | 0.7673 | 0.5921 | 0.7673 | 0.8760 |
|
| 97 |
+
| No log | 1.15 | 92 | 0.8964 | 0.5790 | 0.8964 | 0.9468 |
|
| 98 |
+
| No log | 1.175 | 94 | 0.7913 | 0.5877 | 0.7913 | 0.8895 |
|
| 99 |
+
| No log | 1.2 | 96 | 0.6924 | 0.5751 | 0.6924 | 0.8321 |
|
| 100 |
+
| No log | 1.225 | 98 | 0.6804 | 0.5819 | 0.6804 | 0.8249 |
|
| 101 |
+
| No log | 1.25 | 100 | 0.8491 | 0.5730 | 0.8491 | 0.9215 |
|
| 102 |
+
| No log | 1.275 | 102 | 0.9650 | 0.5187 | 0.9650 | 0.9824 |
|
| 103 |
+
| No log | 1.3 | 104 | 0.8712 | 0.5541 | 0.8712 | 0.9334 |
|
| 104 |
+
| No log | 1.325 | 106 | 0.7316 | 0.5496 | 0.7316 | 0.8554 |
|
| 105 |
+
| No log | 1.35 | 108 | 0.7622 | 0.5500 | 0.7622 | 0.8730 |
|
| 106 |
+
| No log | 1.375 | 110 | 0.7780 | 0.5279 | 0.7780 | 0.8821 |
|
| 107 |
+
| No log | 1.4 | 112 | 0.7609 | 0.5968 | 0.7609 | 0.8723 |
|
| 108 |
+
| No log | 1.425 | 114 | 0.7798 | 0.6583 | 0.7798 | 0.8831 |
|
| 109 |
+
| No log | 1.45 | 116 | 0.8261 | 0.5229 | 0.8261 | 0.9089 |
|
| 110 |
+
| No log | 1.475 | 118 | 0.8550 | 0.5448 | 0.8550 | 0.9247 |
|
| 111 |
+
| No log | 1.5 | 120 | 0.8138 | 0.5532 | 0.8138 | 0.9021 |
|
| 112 |
+
| No log | 1.525 | 122 | 0.8270 | 0.6239 | 0.8270 | 0.9094 |
|
| 113 |
+
| No log | 1.55 | 124 | 0.9004 | 0.5286 | 0.9004 | 0.9489 |
|
| 114 |
+
| No log | 1.575 | 126 | 0.8936 | 0.5266 | 0.8936 | 0.9453 |
|
| 115 |
+
| No log | 1.6 | 128 | 0.8996 | 0.5596 | 0.8996 | 0.9485 |
|
| 116 |
+
| No log | 1.625 | 130 | 0.9849 | 0.4830 | 0.9849 | 0.9924 |
|
| 117 |
+
| No log | 1.65 | 132 | 1.0818 | 0.5140 | 1.0818 | 1.0401 |
|
| 118 |
+
| No log | 1.675 | 134 | 0.9958 | 0.4587 | 0.9958 | 0.9979 |
|
| 119 |
+
| No log | 1.7 | 136 | 0.8366 | 0.5206 | 0.8366 | 0.9147 |
|
| 120 |
+
| No log | 1.725 | 138 | 0.8338 | 0.3816 | 0.8338 | 0.9131 |
|
| 121 |
+
| No log | 1.75 | 140 | 0.8305 | 0.4053 | 0.8305 | 0.9113 |
|
| 122 |
+
| No log | 1.775 | 142 | 0.7574 | 0.5094 | 0.7574 | 0.8703 |
|
| 123 |
+
| No log | 1.8 | 144 | 0.7216 | 0.5578 | 0.7216 | 0.8495 |
|
| 124 |
+
| No log | 1.825 | 146 | 0.7282 | 0.6347 | 0.7282 | 0.8533 |
|
| 125 |
+
| No log | 1.85 | 148 | 0.7583 | 0.6263 | 0.7583 | 0.8708 |
|
| 126 |
+
| No log | 1.875 | 150 | 0.7724 | 0.6341 | 0.7724 | 0.8788 |
|
| 127 |
+
| No log | 1.9 | 152 | 0.7090 | 0.6552 | 0.7090 | 0.8420 |
|
| 128 |
+
| No log | 1.925 | 154 | 0.6944 | 0.6630 | 0.6944 | 0.8333 |
|
| 129 |
+
| No log | 1.95 | 156 | 0.7100 | 0.6399 | 0.7100 | 0.8426 |
|
| 130 |
+
| No log | 1.975 | 158 | 0.7505 | 0.6526 | 0.7505 | 0.8663 |
|
| 131 |
+
| No log | 2.0 | 160 | 0.8198 | 0.6239 | 0.8198 | 0.9055 |
|
| 132 |
+
| No log | 2.025 | 162 | 0.8274 | 0.5823 | 0.8274 | 0.9096 |
|
| 133 |
+
| No log | 2.05 | 164 | 0.7724 | 0.6405 | 0.7724 | 0.8789 |
|
| 134 |
+
| No log | 2.075 | 166 | 0.7719 | 0.6203 | 0.7719 | 0.8786 |
|
| 135 |
+
| No log | 2.1 | 168 | 0.7480 | 0.6251 | 0.7480 | 0.8649 |
|
| 136 |
+
| No log | 2.125 | 170 | 0.7173 | 0.5930 | 0.7173 | 0.8470 |
|
| 137 |
+
| No log | 2.15 | 172 | 0.7477 | 0.5530 | 0.7477 | 0.8647 |
|
| 138 |
+
| No log | 2.175 | 174 | 0.8494 | 0.4728 | 0.8494 | 0.9216 |
|
| 139 |
+
| No log | 2.2 | 176 | 0.9145 | 0.4387 | 0.9145 | 0.9563 |
|
| 140 |
+
| No log | 2.225 | 178 | 0.7806 | 0.6038 | 0.7806 | 0.8835 |
|
| 141 |
+
| No log | 2.25 | 180 | 0.6652 | 0.6393 | 0.6652 | 0.8156 |
|
| 142 |
+
| No log | 2.275 | 182 | 0.6357 | 0.6774 | 0.6357 | 0.7973 |
|
| 143 |
+
| No log | 2.3 | 184 | 0.6438 | 0.6337 | 0.6438 | 0.8024 |
|
| 144 |
+
| No log | 2.325 | 186 | 0.6440 | 0.6025 | 0.6440 | 0.8025 |
|
| 145 |
+
| No log | 2.35 | 188 | 0.6583 | 0.6188 | 0.6583 | 0.8114 |
|
| 146 |
+
| No log | 2.375 | 190 | 0.6423 | 0.5774 | 0.6423 | 0.8015 |
|
| 147 |
+
| No log | 2.4 | 192 | 0.6688 | 0.4923 | 0.6688 | 0.8178 |
|
| 148 |
+
| No log | 2.425 | 194 | 0.6702 | 0.5010 | 0.6702 | 0.8187 |
|
| 149 |
+
| No log | 2.45 | 196 | 0.6690 | 0.5992 | 0.6690 | 0.8179 |
|
| 150 |
+
| No log | 2.475 | 198 | 0.6591 | 0.5869 | 0.6591 | 0.8118 |
|
| 151 |
+
| No log | 2.5 | 200 | 0.6574 | 0.6247 | 0.6574 | 0.8108 |
|
| 152 |
+
| No log | 2.525 | 202 | 0.6613 | 0.6319 | 0.6613 | 0.8132 |
|
| 153 |
+
| No log | 2.55 | 204 | 0.6775 | 0.6484 | 0.6775 | 0.8231 |
|
| 154 |
+
| No log | 2.575 | 206 | 0.6868 | 0.6206 | 0.6868 | 0.8287 |
|
| 155 |
+
| No log | 2.6 | 208 | 0.6980 | 0.6328 | 0.6980 | 0.8355 |
|
| 156 |
+
| No log | 2.625 | 210 | 0.7176 | 0.6001 | 0.7176 | 0.8471 |
|
| 157 |
+
| No log | 2.65 | 212 | 0.7541 | 0.6337 | 0.7541 | 0.8684 |
|
| 158 |
+
| No log | 2.675 | 214 | 0.7485 | 0.6187 | 0.7485 | 0.8651 |
|
| 159 |
+
| No log | 2.7 | 216 | 0.7489 | 0.5786 | 0.7489 | 0.8654 |
|
| 160 |
+
| No log | 2.725 | 218 | 0.7433 | 0.5666 | 0.7433 | 0.8621 |
|
| 161 |
+
| No log | 2.75 | 220 | 0.7157 | 0.5475 | 0.7157 | 0.8460 |
|
| 162 |
+
| No log | 2.775 | 222 | 0.7016 | 0.5455 | 0.7016 | 0.8376 |
|
| 163 |
+
| No log | 2.8 | 224 | 0.7157 | 0.5774 | 0.7157 | 0.8460 |
|
| 164 |
+
| No log | 2.825 | 226 | 0.7055 | 0.5980 | 0.7055 | 0.8399 |
|
| 165 |
+
| No log | 2.85 | 228 | 0.6902 | 0.5928 | 0.6902 | 0.8308 |
|
| 166 |
+
| No log | 2.875 | 230 | 0.6936 | 0.5492 | 0.6936 | 0.8328 |
|
| 167 |
+
| No log | 2.9 | 232 | 0.6981 | 0.5606 | 0.6981 | 0.8355 |
|
| 168 |
+
| No log | 2.925 | 234 | 0.6997 | 0.5877 | 0.6997 | 0.8365 |
|
| 169 |
+
| No log | 2.95 | 236 | 0.7068 | 0.5853 | 0.7068 | 0.8407 |
|
| 170 |
+
| No log | 2.975 | 238 | 0.7017 | 0.5853 | 0.7017 | 0.8377 |
|
| 171 |
+
| No log | 3.0 | 240 | 0.6934 | 0.6114 | 0.6934 | 0.8327 |
|
| 172 |
+
| No log | 3.025 | 242 | 0.6893 | 0.5512 | 0.6893 | 0.8302 |
|
| 173 |
+
| No log | 3.05 | 244 | 0.7120 | 0.6070 | 0.7120 | 0.8438 |
|
| 174 |
+
| No log | 3.075 | 246 | 0.6863 | 0.6215 | 0.6863 | 0.8285 |
|
| 175 |
+
| No log | 3.1 | 248 | 0.6796 | 0.6297 | 0.6796 | 0.8244 |
|
| 176 |
+
| No log | 3.125 | 250 | 0.7309 | 0.5921 | 0.7309 | 0.8549 |
|
| 177 |
+
| No log | 3.15 | 252 | 0.6916 | 0.6421 | 0.6916 | 0.8316 |
|
| 178 |
+
| No log | 3.175 | 254 | 0.6605 | 0.6796 | 0.6605 | 0.8127 |
|
| 179 |
+
| No log | 3.2 | 256 | 0.6702 | 0.6368 | 0.6702 | 0.8187 |
|
| 180 |
+
| No log | 3.225 | 258 | 0.6503 | 0.6398 | 0.6503 | 0.8064 |
|
| 181 |
+
| No log | 3.25 | 260 | 0.6669 | 0.5980 | 0.6669 | 0.8166 |
|
| 182 |
+
| No log | 3.275 | 262 | 0.6897 | 0.5654 | 0.6897 | 0.8305 |
|
| 183 |
+
| No log | 3.3 | 264 | 0.6843 | 0.5156 | 0.6843 | 0.8272 |
|
| 184 |
+
| No log | 3.325 | 266 | 0.7012 | 0.5635 | 0.7012 | 0.8374 |
|
| 185 |
+
| No log | 3.35 | 268 | 0.7246 | 0.5828 | 0.7246 | 0.8512 |
|
| 186 |
+
| No log | 3.375 | 270 | 0.7057 | 0.6046 | 0.7057 | 0.8401 |
|
| 187 |
+
| No log | 3.4 | 272 | 0.7184 | 0.5774 | 0.7184 | 0.8476 |
|
| 188 |
+
| No log | 3.425 | 274 | 0.7550 | 0.5654 | 0.7550 | 0.8689 |
|
| 189 |
+
| No log | 3.45 | 276 | 0.7339 | 0.5654 | 0.7339 | 0.8567 |
|
| 190 |
+
| No log | 3.475 | 278 | 0.7017 | 0.6035 | 0.7017 | 0.8377 |
|
| 191 |
+
| No log | 3.5 | 280 | 0.7203 | 0.5287 | 0.7203 | 0.8487 |
|
| 192 |
+
| No log | 3.525 | 282 | 0.7455 | 0.5198 | 0.7455 | 0.8634 |
|
| 193 |
+
| No log | 3.55 | 284 | 0.7362 | 0.5794 | 0.7362 | 0.8580 |
|
| 194 |
+
| No log | 3.575 | 286 | 0.7144 | 0.5752 | 0.7144 | 0.8452 |
|
| 195 |
+
| No log | 3.6 | 288 | 0.6964 | 0.5866 | 0.6964 | 0.8345 |
|
| 196 |
+
| No log | 3.625 | 290 | 0.6835 | 0.6154 | 0.6835 | 0.8268 |
|
| 197 |
+
| No log | 3.65 | 292 | 0.7301 | 0.5653 | 0.7301 | 0.8544 |
|
| 198 |
+
| No log | 3.675 | 294 | 0.7594 | 0.5759 | 0.7594 | 0.8715 |
|
| 199 |
+
| No log | 3.7 | 296 | 0.7283 | 0.6345 | 0.7283 | 0.8534 |
|
| 200 |
+
| No log | 3.725 | 298 | 0.7133 | 0.6337 | 0.7133 | 0.8446 |
|
| 201 |
+
| No log | 3.75 | 300 | 0.7077 | 0.6350 | 0.7077 | 0.8413 |
|
| 202 |
+
| No log | 3.775 | 302 | 0.7094 | 0.5985 | 0.7094 | 0.8423 |
|
| 203 |
+
| No log | 3.8 | 304 | 0.7078 | 0.6217 | 0.7078 | 0.8413 |
|
| 204 |
+
| No log | 3.825 | 306 | 0.7041 | 0.5467 | 0.7041 | 0.8391 |
|
| 205 |
+
| No log | 3.85 | 308 | 0.7025 | 0.5558 | 0.7025 | 0.8381 |
|
| 206 |
+
| No log | 3.875 | 310 | 0.7114 | 0.5774 | 0.7114 | 0.8434 |
|
| 207 |
+
| No log | 3.9 | 312 | 0.7212 | 0.6254 | 0.7212 | 0.8492 |
|
| 208 |
+
| No log | 3.925 | 314 | 0.7851 | 0.5604 | 0.7851 | 0.8860 |
|
| 209 |
+
| No log | 3.95 | 316 | 0.7470 | 0.5698 | 0.7470 | 0.8643 |
|
| 210 |
+
| No log | 3.975 | 318 | 0.6744 | 0.6306 | 0.6744 | 0.8212 |
|
| 211 |
+
| No log | 4.0 | 320 | 0.6891 | 0.6100 | 0.6891 | 0.8301 |
|
| 212 |
+
| No log | 4.025 | 322 | 0.7000 | 0.6138 | 0.7000 | 0.8367 |
|
| 213 |
+
| No log | 4.05 | 324 | 0.6942 | 0.6138 | 0.6942 | 0.8332 |
|
| 214 |
+
| No log | 4.075 | 326 | 0.7046 | 0.6404 | 0.7046 | 0.8394 |
|
| 215 |
+
| No log | 4.1 | 328 | 0.6879 | 0.5796 | 0.6879 | 0.8294 |
|
| 216 |
+
| No log | 4.125 | 330 | 0.6947 | 0.5483 | 0.6947 | 0.8335 |
|
| 217 |
+
| No log | 4.15 | 332 | 0.6950 | 0.5902 | 0.6950 | 0.8336 |
|
| 218 |
+
| No log | 4.175 | 334 | 0.7298 | 0.6035 | 0.7298 | 0.8543 |
|
| 219 |
+
| No log | 4.2 | 336 | 0.7365 | 0.5595 | 0.7365 | 0.8582 |
|
| 220 |
+
| No log | 4.225 | 338 | 0.7131 | 0.5343 | 0.7131 | 0.8445 |
|
| 221 |
+
| No log | 4.25 | 340 | 0.7418 | 0.5554 | 0.7418 | 0.8613 |
|
| 222 |
+
| No log | 4.275 | 342 | 0.7609 | 0.5554 | 0.7609 | 0.8723 |
|
| 223 |
+
| No log | 4.3 | 344 | 0.7617 | 0.5325 | 0.7617 | 0.8727 |
|
| 224 |
+
| No log | 4.325 | 346 | 0.7231 | 0.5633 | 0.7231 | 0.8503 |
|
| 225 |
+
| No log | 4.35 | 348 | 0.7205 | 0.5632 | 0.7205 | 0.8488 |
|
| 226 |
+
| No log | 4.375 | 350 | 0.7729 | 0.6411 | 0.7729 | 0.8791 |
|
| 227 |
+
| No log | 4.4 | 352 | 0.8049 | 0.5911 | 0.8049 | 0.8972 |
|
| 228 |
+
| No log | 4.425 | 354 | 0.7518 | 0.5882 | 0.7518 | 0.8671 |
|
| 229 |
+
| No log | 4.45 | 356 | 0.7126 | 0.6439 | 0.7126 | 0.8441 |
|
| 230 |
+
| No log | 4.475 | 358 | 0.6987 | 0.6440 | 0.6987 | 0.8359 |
|
| 231 |
+
| No log | 4.5 | 360 | 0.6940 | 0.6570 | 0.6940 | 0.8331 |
|
| 232 |
+
| No log | 4.525 | 362 | 0.7084 | 0.6281 | 0.7084 | 0.8417 |
|
| 233 |
+
| No log | 4.55 | 364 | 0.7367 | 0.5815 | 0.7367 | 0.8583 |
|
| 234 |
+
| No log | 4.575 | 366 | 0.7267 | 0.6038 | 0.7267 | 0.8525 |
|
| 235 |
+
| No log | 4.6 | 368 | 0.6939 | 0.6112 | 0.6939 | 0.8330 |
|
| 236 |
+
| No log | 4.625 | 370 | 0.6873 | 0.6226 | 0.6873 | 0.8290 |
|
| 237 |
+
| No log | 4.65 | 372 | 0.6752 | 0.6045 | 0.6752 | 0.8217 |
|
| 238 |
+
| No log | 4.675 | 374 | 0.6561 | 0.5996 | 0.6561 | 0.8100 |
|
| 239 |
+
| No log | 4.7 | 376 | 0.6549 | 0.5084 | 0.6549 | 0.8093 |
|
| 240 |
+
| No log | 4.725 | 378 | 0.6682 | 0.5102 | 0.6682 | 0.8174 |
|
| 241 |
+
| No log | 4.75 | 380 | 0.6387 | 0.5905 | 0.6387 | 0.7992 |
|
| 242 |
+
| No log | 4.775 | 382 | 0.6248 | 0.6564 | 0.6248 | 0.7904 |
|
| 243 |
+
| No log | 4.8 | 384 | 0.6266 | 0.6455 | 0.6266 | 0.7916 |
|
| 244 |
+
| No log | 4.825 | 386 | 0.6037 | 0.6610 | 0.6037 | 0.7770 |
|
| 245 |
+
| No log | 4.85 | 388 | 0.6014 | 0.6874 | 0.6014 | 0.7755 |
|
| 246 |
+
| No log | 4.875 | 390 | 0.6024 | 0.6649 | 0.6024 | 0.7762 |
|
| 247 |
+
| No log | 4.9 | 392 | 0.6072 | 0.6345 | 0.6072 | 0.7793 |
|
| 248 |
+
| No log | 4.925 | 394 | 0.6076 | 0.6380 | 0.6076 | 0.7795 |
|
| 249 |
+
| No log | 4.95 | 396 | 0.6134 | 0.5921 | 0.6134 | 0.7832 |
|
| 250 |
+
| No log | 4.975 | 398 | 0.6306 | 0.5676 | 0.6306 | 0.7941 |
|
| 251 |
+
| No log | 5.0 | 400 | 0.6200 | 0.5921 | 0.6200 | 0.7874 |
|
| 252 |
+
| No log | 5.025 | 402 | 0.6274 | 0.5921 | 0.6274 | 0.7921 |
|
| 253 |
+
| No log | 5.05 | 404 | 0.6270 | 0.5774 | 0.6270 | 0.7918 |
|
| 254 |
+
| No log | 5.075 | 406 | 0.6439 | 0.5634 | 0.6439 | 0.8024 |
|
| 255 |
+
| No log | 5.1 | 408 | 0.6703 | 0.5634 | 0.6703 | 0.8187 |
|
| 256 |
+
| No log | 5.125 | 410 | 0.6653 | 0.5948 | 0.6653 | 0.8157 |
|
| 257 |
+
| No log | 5.15 | 412 | 0.6646 | 0.5751 | 0.6646 | 0.8152 |
|
| 258 |
+
| No log | 5.175 | 414 | 0.6555 | 0.5810 | 0.6555 | 0.8097 |
|
| 259 |
+
| No log | 5.2 | 416 | 0.6534 | 0.5156 | 0.6534 | 0.8083 |
|
| 260 |
+
| No log | 5.225 | 418 | 0.6937 | 0.4588 | 0.6937 | 0.8329 |
|
| 261 |
+
| No log | 5.25 | 420 | 0.7017 | 0.4725 | 0.7017 | 0.8377 |
|
| 262 |
+
| No log | 5.275 | 422 | 0.6605 | 0.5782 | 0.6605 | 0.8127 |
|
| 263 |
+
| No log | 5.3 | 424 | 0.6192 | 0.6555 | 0.6192 | 0.7869 |
|
| 264 |
+
| No log | 5.325 | 426 | 0.6379 | 0.6288 | 0.6379 | 0.7987 |
|
| 265 |
+
| No log | 5.35 | 428 | 0.6979 | 0.6669 | 0.6979 | 0.8354 |
|
| 266 |
+
| No log | 5.375 | 430 | 0.6847 | 0.6538 | 0.6847 | 0.8275 |
|
| 267 |
+
| No log | 5.4 | 432 | 0.6406 | 0.6197 | 0.6406 | 0.8004 |
|
| 268 |
+
| No log | 5.425 | 434 | 0.6350 | 0.6473 | 0.6350 | 0.7969 |
|
| 269 |
+
| No log | 5.45 | 436 | 0.6434 | 0.6009 | 0.6434 | 0.8021 |
|
| 270 |
+
| No log | 5.475 | 438 | 0.6326 | 0.5945 | 0.6326 | 0.7954 |
|
| 271 |
+
| No log | 5.5 | 440 | 0.6297 | 0.6292 | 0.6297 | 0.7935 |
|
| 272 |
+
| No log | 5.525 | 442 | 0.6436 | 0.6383 | 0.6436 | 0.8022 |
|
| 273 |
+
| No log | 5.55 | 444 | 0.6428 | 0.6499 | 0.6428 | 0.8017 |
|
| 274 |
+
| No log | 5.575 | 446 | 0.6449 | 0.6499 | 0.6449 | 0.8031 |
|
| 275 |
+
| No log | 5.6 | 448 | 0.6546 | 0.6377 | 0.6546 | 0.8091 |
|
| 276 |
+
| No log | 5.625 | 450 | 0.6641 | 0.5852 | 0.6641 | 0.8149 |
|
| 277 |
+
| No log | 5.65 | 452 | 0.6594 | 0.5852 | 0.6594 | 0.8120 |
|
| 278 |
+
| No log | 5.675 | 454 | 0.6279 | 0.6364 | 0.6279 | 0.7924 |
|
| 279 |
+
| No log | 5.7 | 456 | 0.6244 | 0.6619 | 0.6244 | 0.7902 |
|
| 280 |
+
| No log | 5.725 | 458 | 0.6300 | 0.6345 | 0.6300 | 0.7937 |
|
| 281 |
+
| No log | 5.75 | 460 | 0.6614 | 0.6221 | 0.6614 | 0.8132 |
|
| 282 |
+
| No log | 5.775 | 462 | 0.6366 | 0.6368 | 0.6366 | 0.7979 |
|
| 283 |
+
| No log | 5.8 | 464 | 0.6299 | 0.6060 | 0.6299 | 0.7937 |
|
| 284 |
+
| No log | 5.825 | 466 | 0.6340 | 0.5656 | 0.6340 | 0.7963 |
|
| 285 |
+
| No log | 5.85 | 468 | 0.6441 | 0.5656 | 0.6441 | 0.8025 |
|
| 286 |
+
| No log | 5.875 | 470 | 0.6591 | 0.5125 | 0.6591 | 0.8118 |
|
| 287 |
+
| No log | 5.9 | 472 | 0.6666 | 0.5356 | 0.6666 | 0.8164 |
|
| 288 |
+
| No log | 5.925 | 474 | 0.6714 | 0.6022 | 0.6714 | 0.8194 |
|
| 289 |
+
| No log | 5.95 | 476 | 0.6821 | 0.5960 | 0.6821 | 0.8259 |
|
| 290 |
+
| No log | 5.975 | 478 | 0.6867 | 0.5946 | 0.6867 | 0.8287 |
|
| 291 |
+
| No log | 6.0 | 480 | 0.6804 | 0.5946 | 0.6804 | 0.8249 |
|
| 292 |
+
| No log | 6.025 | 482 | 0.6463 | 0.5989 | 0.6463 | 0.8039 |
|
| 293 |
+
| No log | 6.05 | 484 | 0.6394 | 0.6217 | 0.6394 | 0.7996 |
|
| 294 |
+
| No log | 6.075 | 486 | 0.6369 | 0.6018 | 0.6369 | 0.7980 |
|
| 295 |
+
| No log | 6.1 | 488 | 0.6403 | 0.5966 | 0.6403 | 0.8002 |
|
| 296 |
+
| No log | 6.125 | 490 | 0.6579 | 0.5428 | 0.6579 | 0.8111 |
|
| 297 |
+
| No log | 6.15 | 492 | 0.6603 | 0.5966 | 0.6603 | 0.8126 |
|
| 298 |
+
| No log | 6.175 | 494 | 0.6593 | 0.5985 | 0.6593 | 0.8120 |
|
| 299 |
+
| No log | 6.2 | 496 | 0.6616 | 0.5995 | 0.6616 | 0.8134 |
|
| 300 |
+
| No log | 6.225 | 498 | 0.6592 | 0.5797 | 0.6592 | 0.8119 |
|
| 301 |
+
| 0.3107 | 6.25 | 500 | 0.6565 | 0.5797 | 0.6565 | 0.8103 |
|
| 302 |
+
| 0.3107 | 6.275 | 502 | 0.6513 | 0.5747 | 0.6513 | 0.8070 |
|
| 303 |
+
| 0.3107 | 6.3 | 504 | 0.6485 | 0.5747 | 0.6485 | 0.8053 |
|
| 304 |
+
| 0.3107 | 6.325 | 506 | 0.6576 | 0.6262 | 0.6576 | 0.8109 |
|
| 305 |
+
| 0.3107 | 6.35 | 508 | 0.6625 | 0.5747 | 0.6625 | 0.8140 |
|
| 306 |
+
| 0.3107 | 6.375 | 510 | 0.6849 | 0.5518 | 0.6849 | 0.8276 |
|
| 307 |
+
| 0.3107 | 6.4 | 512 | 0.7166 | 0.5604 | 0.7166 | 0.8465 |
|
| 308 |
+
| 0.3107 | 6.425 | 514 | 0.7014 | 0.6056 | 0.7014 | 0.8375 |
|
| 309 |
+
| 0.3107 | 6.45 | 516 | 0.6661 | 0.6385 | 0.6661 | 0.8162 |
|
| 310 |
+
| 0.3107 | 6.475 | 518 | 0.6513 | 0.6157 | 0.6513 | 0.8070 |
|
| 311 |
+
| 0.3107 | 6.5 | 520 | 0.6268 | 0.6407 | 0.6268 | 0.7917 |
|
| 312 |
+
| 0.3107 | 6.525 | 522 | 0.6193 | 0.6105 | 0.6193 | 0.7869 |
|
| 313 |
+
| 0.3107 | 6.55 | 524 | 0.6154 | 0.6242 | 0.6154 | 0.7845 |
|
| 314 |
+
| 0.3107 | 6.575 | 526 | 0.6328 | 0.6116 | 0.6328 | 0.7955 |
|
| 315 |
+
| 0.3107 | 6.6 | 528 | 0.6503 | 0.5922 | 0.6503 | 0.8064 |
|
| 316 |
+
| 0.3107 | 6.625 | 530 | 0.6323 | 0.5902 | 0.6323 | 0.7952 |
|
| 317 |
+
| 0.3107 | 6.65 | 532 | 0.6299 | 0.5506 | 0.6299 | 0.7936 |
|
| 318 |
+
| 0.3107 | 6.675 | 534 | 0.6430 | 0.5055 | 0.6430 | 0.8018 |
|
| 319 |
+
| 0.3107 | 6.7 | 536 | 0.6550 | 0.5913 | 0.6550 | 0.8093 |
|
| 320 |
+
| 0.3107 | 6.725 | 538 | 0.6607 | 0.5261 | 0.6607 | 0.8128 |
|
| 321 |
+
| 0.3107 | 6.75 | 540 | 0.6838 | 0.5434 | 0.6838 | 0.8269 |
|
| 322 |
+
| 0.3107 | 6.775 | 542 | 0.7004 | 0.5430 | 0.7004 | 0.8369 |
|
| 323 |
+
| 0.3107 | 6.8 | 544 | 0.6775 | 0.5726 | 0.6775 | 0.8231 |
|
| 324 |
+
| 0.3107 | 6.825 | 546 | 0.6772 | 0.6084 | 0.6772 | 0.8229 |
|
| 325 |
+
| 0.3107 | 6.85 | 548 | 0.7588 | 0.5788 | 0.7588 | 0.8711 |
|
| 326 |
+
| 0.3107 | 6.875 | 550 | 0.7881 | 0.5621 | 0.7881 | 0.8877 |
|
| 327 |
+
| 0.3107 | 6.9 | 552 | 0.7471 | 0.5477 | 0.7471 | 0.8643 |
|
| 328 |
+
| 0.3107 | 6.925 | 554 | 0.7036 | 0.5959 | 0.7036 | 0.8388 |
|
| 329 |
+
| 0.3107 | 6.95 | 556 | 0.6685 | 0.5582 | 0.6685 | 0.8176 |
|
| 330 |
+
| 0.3107 | 6.975 | 558 | 0.6631 | 0.5582 | 0.6631 | 0.8143 |
|
| 331 |
+
| 0.3107 | 7.0 | 560 | 0.6641 | 0.5563 | 0.6641 | 0.8150 |
|
| 332 |
+
| 0.3107 | 7.025 | 562 | 0.6507 | 0.5975 | 0.6507 | 0.8067 |
|
| 333 |
+
| 0.3107 | 7.05 | 564 | 0.6501 | 0.6157 | 0.6501 | 0.8063 |
|
| 334 |
+
| 0.3107 | 7.075 | 566 | 0.6512 | 0.6157 | 0.6512 | 0.8069 |
|
| 335 |
+
| 0.3107 | 7.1 | 568 | 0.6449 | 0.5975 | 0.6449 | 0.8030 |
|
| 336 |
+
| 0.3107 | 7.125 | 570 | 0.6623 | 0.6464 | 0.6623 | 0.8138 |
|
| 337 |
+
| 0.3107 | 7.15 | 572 | 0.6876 | 0.6347 | 0.6876 | 0.8292 |
|
| 338 |
+
| 0.3107 | 7.175 | 574 | 0.7006 | 0.5729 | 0.7006 | 0.8370 |
|
| 339 |
+
| 0.3107 | 7.2 | 576 | 0.6626 | 0.6113 | 0.6626 | 0.8140 |
|
| 340 |
+
| 0.3107 | 7.225 | 578 | 0.6359 | 0.5606 | 0.6359 | 0.7974 |
|
| 341 |
+
| 0.3107 | 7.25 | 580 | 0.6293 | 0.5988 | 0.6293 | 0.7933 |
|
| 342 |
+
| 0.3107 | 7.275 | 582 | 0.6157 | 0.5606 | 0.6157 | 0.7846 |
|
| 343 |
+
| 0.3107 | 7.3 | 584 | 0.6178 | 0.6269 | 0.6178 | 0.7860 |
|
| 344 |
+
| 0.3107 | 7.325 | 586 | 0.6272 | 0.6626 | 0.6272 | 0.7920 |
|
| 345 |
+
| 0.3107 | 7.35 | 588 | 0.6540 | 0.6632 | 0.6540 | 0.8087 |
|
| 346 |
+
| 0.3107 | 7.375 | 590 | 0.6480 | 0.6632 | 0.6480 | 0.8050 |
|
| 347 |
+
| 0.3107 | 7.4 | 592 | 0.6322 | 0.6468 | 0.6322 | 0.7951 |
|
| 348 |
+
| 0.3107 | 7.425 | 594 | 0.6121 | 0.6113 | 0.6121 | 0.7823 |
|
| 349 |
+
| 0.3107 | 7.45 | 596 | 0.6092 | 0.6325 | 0.6092 | 0.7805 |
|
| 350 |
+
| 0.3107 | 7.475 | 598 | 0.6604 | 0.6330 | 0.6604 | 0.8127 |
|
| 351 |
+
| 0.3107 | 7.5 | 600 | 0.7239 | 0.5823 | 0.7239 | 0.8508 |
|
| 352 |
+
| 0.3107 | 7.525 | 602 | 0.7303 | 0.5823 | 0.7303 | 0.8546 |
|
| 353 |
+
| 0.3107 | 7.55 | 604 | 0.6779 | 0.6144 | 0.6779 | 0.8234 |
|
| 354 |
+
| 0.3107 | 7.575 | 606 | 0.6519 | 0.5614 | 0.6519 | 0.8074 |
|
| 355 |
+
| 0.3107 | 7.6 | 608 | 0.6598 | 0.5386 | 0.6598 | 0.8123 |
|
| 356 |
+
| 0.3107 | 7.625 | 610 | 0.6570 | 0.5288 | 0.6570 | 0.8106 |
|
| 357 |
+
| 0.3107 | 7.65 | 612 | 0.6667 | 0.5679 | 0.6667 | 0.8165 |
|
| 358 |
+
| 0.3107 | 7.675 | 614 | 0.6822 | 0.5681 | 0.6822 | 0.8260 |
|
| 359 |
+
|
| 360 |
+
|
| 361 |
+
### Framework versions
|
| 362 |
+
|
| 363 |
+
- Transformers 4.44.2
|
| 364 |
+
- Pytorch 2.4.0+cu118
|
| 365 |
+
- Datasets 2.21.0
|
| 366 |
+
- 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:c4d4f0c032c74cba745b942ad0e9c4bb5fac1110c8a4bc43853507e2b9c24f04
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3efc284509dc3e6d81e60202bb1a1f9779fa90a78793bb782d89980e058533e0
|
| 3 |
+
size 5304
|