Training in progress, step 500
Browse files- README.md +356 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask1_development
|
| 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 |
+
# Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask1_development
|
| 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: 0.4088
|
| 19 |
+
- Qwk: 0.5376
|
| 20 |
+
- Mse: 0.4088
|
| 21 |
+
- Rmse: 0.6394
|
| 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 | 0.0213 | 2 | 3.9661 | 0.0006 | 3.9661 | 1.9915 |
|
| 53 |
+
| No log | 0.0426 | 4 | 2.8142 | 0.0570 | 2.8142 | 1.6775 |
|
| 54 |
+
| No log | 0.0638 | 6 | 1.3758 | 0.0502 | 1.3758 | 1.1729 |
|
| 55 |
+
| No log | 0.0851 | 8 | 0.8573 | 0.0440 | 0.8573 | 0.9259 |
|
| 56 |
+
| No log | 0.1064 | 10 | 0.7581 | 0.0668 | 0.7581 | 0.8707 |
|
| 57 |
+
| No log | 0.1277 | 12 | 0.7360 | 0.0830 | 0.7360 | 0.8579 |
|
| 58 |
+
| No log | 0.1489 | 14 | 0.6776 | 0.0832 | 0.6776 | 0.8232 |
|
| 59 |
+
| No log | 0.1702 | 16 | 0.6691 | 0.3161 | 0.6691 | 0.8180 |
|
| 60 |
+
| No log | 0.1915 | 18 | 0.6032 | 0.3937 | 0.6032 | 0.7767 |
|
| 61 |
+
| No log | 0.2128 | 20 | 0.5791 | 0.3812 | 0.5791 | 0.7610 |
|
| 62 |
+
| No log | 0.2340 | 22 | 0.6016 | 0.3765 | 0.6016 | 0.7757 |
|
| 63 |
+
| No log | 0.2553 | 24 | 0.6617 | 0.3275 | 0.6617 | 0.8135 |
|
| 64 |
+
| No log | 0.2766 | 26 | 0.6540 | 0.3498 | 0.6540 | 0.8087 |
|
| 65 |
+
| No log | 0.2979 | 28 | 0.5786 | 0.3889 | 0.5786 | 0.7607 |
|
| 66 |
+
| No log | 0.3191 | 30 | 0.5534 | 0.3950 | 0.5534 | 0.7439 |
|
| 67 |
+
| No log | 0.3404 | 32 | 0.6693 | 0.2150 | 0.6693 | 0.8181 |
|
| 68 |
+
| No log | 0.3617 | 34 | 0.6927 | 0.2867 | 0.6927 | 0.8323 |
|
| 69 |
+
| No log | 0.3830 | 36 | 0.5389 | 0.4632 | 0.5389 | 0.7341 |
|
| 70 |
+
| No log | 0.4043 | 38 | 0.5280 | 0.4822 | 0.5280 | 0.7266 |
|
| 71 |
+
| No log | 0.4255 | 40 | 0.5358 | 0.4835 | 0.5358 | 0.7320 |
|
| 72 |
+
| No log | 0.4468 | 42 | 0.4939 | 0.4966 | 0.4939 | 0.7028 |
|
| 73 |
+
| No log | 0.4681 | 44 | 0.4797 | 0.5075 | 0.4797 | 0.6926 |
|
| 74 |
+
| No log | 0.4894 | 46 | 0.4909 | 0.4695 | 0.4909 | 0.7006 |
|
| 75 |
+
| No log | 0.5106 | 48 | 0.4905 | 0.4695 | 0.4905 | 0.7004 |
|
| 76 |
+
| No log | 0.5319 | 50 | 0.4793 | 0.5410 | 0.4793 | 0.6923 |
|
| 77 |
+
| No log | 0.5532 | 52 | 0.5706 | 0.5437 | 0.5706 | 0.7554 |
|
| 78 |
+
| No log | 0.5745 | 54 | 0.5039 | 0.5471 | 0.5039 | 0.7098 |
|
| 79 |
+
| No log | 0.5957 | 56 | 0.4814 | 0.4922 | 0.4814 | 0.6938 |
|
| 80 |
+
| No log | 0.6170 | 58 | 0.4793 | 0.4941 | 0.4793 | 0.6923 |
|
| 81 |
+
| No log | 0.6383 | 60 | 0.4930 | 0.4755 | 0.4930 | 0.7021 |
|
| 82 |
+
| No log | 0.6596 | 62 | 0.5077 | 0.4415 | 0.5077 | 0.7125 |
|
| 83 |
+
| No log | 0.6809 | 64 | 0.5329 | 0.4281 | 0.5329 | 0.7300 |
|
| 84 |
+
| No log | 0.7021 | 66 | 0.4572 | 0.5173 | 0.4572 | 0.6762 |
|
| 85 |
+
| No log | 0.7234 | 68 | 0.4331 | 0.5397 | 0.4331 | 0.6581 |
|
| 86 |
+
| No log | 0.7447 | 70 | 0.4294 | 0.5499 | 0.4294 | 0.6553 |
|
| 87 |
+
| No log | 0.7660 | 72 | 0.4208 | 0.5787 | 0.4208 | 0.6487 |
|
| 88 |
+
| No log | 0.7872 | 74 | 0.4638 | 0.5604 | 0.4638 | 0.6810 |
|
| 89 |
+
| No log | 0.8085 | 76 | 0.4346 | 0.5684 | 0.4346 | 0.6592 |
|
| 90 |
+
| No log | 0.8298 | 78 | 0.4511 | 0.5609 | 0.4511 | 0.6716 |
|
| 91 |
+
| No log | 0.8511 | 80 | 0.4506 | 0.6079 | 0.4506 | 0.6713 |
|
| 92 |
+
| No log | 0.8723 | 82 | 0.4315 | 0.5578 | 0.4315 | 0.6569 |
|
| 93 |
+
| No log | 0.8936 | 84 | 0.4510 | 0.5739 | 0.4510 | 0.6716 |
|
| 94 |
+
| No log | 0.9149 | 86 | 0.6624 | 0.3852 | 0.6624 | 0.8139 |
|
| 95 |
+
| No log | 0.9362 | 88 | 0.7905 | 0.1659 | 0.7905 | 0.8891 |
|
| 96 |
+
| No log | 0.9574 | 90 | 0.7080 | 0.2767 | 0.7080 | 0.8414 |
|
| 97 |
+
| No log | 0.9787 | 92 | 0.5450 | 0.4255 | 0.5450 | 0.7382 |
|
| 98 |
+
| No log | 1.0 | 94 | 0.4271 | 0.5839 | 0.4271 | 0.6535 |
|
| 99 |
+
| No log | 1.0213 | 96 | 0.4668 | 0.6117 | 0.4668 | 0.6833 |
|
| 100 |
+
| No log | 1.0426 | 98 | 0.4931 | 0.6038 | 0.4931 | 0.7022 |
|
| 101 |
+
| No log | 1.0638 | 100 | 0.4532 | 0.6076 | 0.4532 | 0.6732 |
|
| 102 |
+
| No log | 1.0851 | 102 | 0.4919 | 0.6031 | 0.4919 | 0.7013 |
|
| 103 |
+
| No log | 1.1064 | 104 | 0.5006 | 0.5543 | 0.5006 | 0.7075 |
|
| 104 |
+
| No log | 1.1277 | 106 | 0.4613 | 0.5426 | 0.4613 | 0.6792 |
|
| 105 |
+
| No log | 1.1489 | 108 | 0.4891 | 0.5035 | 0.4891 | 0.6993 |
|
| 106 |
+
| No log | 1.1702 | 110 | 0.5031 | 0.4745 | 0.5031 | 0.7093 |
|
| 107 |
+
| No log | 1.1915 | 112 | 0.4780 | 0.4819 | 0.4780 | 0.6914 |
|
| 108 |
+
| No log | 1.2128 | 114 | 0.4851 | 0.4873 | 0.4851 | 0.6965 |
|
| 109 |
+
| No log | 1.2340 | 116 | 0.4726 | 0.5470 | 0.4726 | 0.6875 |
|
| 110 |
+
| No log | 1.2553 | 118 | 0.4432 | 0.5399 | 0.4432 | 0.6657 |
|
| 111 |
+
| No log | 1.2766 | 120 | 0.4471 | 0.5840 | 0.4471 | 0.6687 |
|
| 112 |
+
| No log | 1.2979 | 122 | 0.4497 | 0.5659 | 0.4497 | 0.6706 |
|
| 113 |
+
| No log | 1.3191 | 124 | 0.5107 | 0.5062 | 0.5107 | 0.7146 |
|
| 114 |
+
| No log | 1.3404 | 126 | 0.4501 | 0.5327 | 0.4501 | 0.6709 |
|
| 115 |
+
| No log | 1.3617 | 128 | 0.4368 | 0.5911 | 0.4368 | 0.6609 |
|
| 116 |
+
| No log | 1.3830 | 130 | 0.4683 | 0.5990 | 0.4683 | 0.6844 |
|
| 117 |
+
| No log | 1.4043 | 132 | 0.6832 | 0.5579 | 0.6832 | 0.8266 |
|
| 118 |
+
| No log | 1.4255 | 134 | 0.7875 | 0.4894 | 0.7875 | 0.8874 |
|
| 119 |
+
| No log | 1.4468 | 136 | 0.6340 | 0.5699 | 0.6340 | 0.7962 |
|
| 120 |
+
| No log | 1.4681 | 138 | 0.5137 | 0.5868 | 0.5137 | 0.7167 |
|
| 121 |
+
| No log | 1.4894 | 140 | 0.4678 | 0.5620 | 0.4678 | 0.6840 |
|
| 122 |
+
| No log | 1.5106 | 142 | 0.4385 | 0.5585 | 0.4385 | 0.6622 |
|
| 123 |
+
| No log | 1.5319 | 144 | 0.4237 | 0.6041 | 0.4237 | 0.6509 |
|
| 124 |
+
| No log | 1.5532 | 146 | 0.4305 | 0.5749 | 0.4305 | 0.6562 |
|
| 125 |
+
| No log | 1.5745 | 148 | 0.5813 | 0.5527 | 0.5813 | 0.7624 |
|
| 126 |
+
| No log | 1.5957 | 150 | 0.6819 | 0.4978 | 0.6819 | 0.8258 |
|
| 127 |
+
| No log | 1.6170 | 152 | 0.7632 | 0.5356 | 0.7632 | 0.8736 |
|
| 128 |
+
| No log | 1.6383 | 154 | 0.6873 | 0.5606 | 0.6873 | 0.8290 |
|
| 129 |
+
| No log | 1.6596 | 156 | 0.5527 | 0.6069 | 0.5527 | 0.7434 |
|
| 130 |
+
| No log | 1.6809 | 158 | 0.4914 | 0.6235 | 0.4914 | 0.7010 |
|
| 131 |
+
| No log | 1.7021 | 160 | 0.4513 | 0.5698 | 0.4513 | 0.6718 |
|
| 132 |
+
| No log | 1.7234 | 162 | 0.4922 | 0.5259 | 0.4922 | 0.7016 |
|
| 133 |
+
| No log | 1.7447 | 164 | 0.5357 | 0.4956 | 0.5357 | 0.7319 |
|
| 134 |
+
| No log | 1.7660 | 166 | 0.6366 | 0.4833 | 0.6366 | 0.7979 |
|
| 135 |
+
| No log | 1.7872 | 168 | 0.6920 | 0.4236 | 0.6920 | 0.8319 |
|
| 136 |
+
| No log | 1.8085 | 170 | 0.5774 | 0.4567 | 0.5774 | 0.7599 |
|
| 137 |
+
| No log | 1.8298 | 172 | 0.4541 | 0.4634 | 0.4541 | 0.6739 |
|
| 138 |
+
| No log | 1.8511 | 174 | 0.4664 | 0.4809 | 0.4664 | 0.6829 |
|
| 139 |
+
| No log | 1.8723 | 176 | 0.4637 | 0.5181 | 0.4637 | 0.6810 |
|
| 140 |
+
| No log | 1.8936 | 178 | 0.4448 | 0.5077 | 0.4448 | 0.6669 |
|
| 141 |
+
| No log | 1.9149 | 180 | 0.4541 | 0.4803 | 0.4541 | 0.6739 |
|
| 142 |
+
| No log | 1.9362 | 182 | 0.4787 | 0.4465 | 0.4787 | 0.6919 |
|
| 143 |
+
| No log | 1.9574 | 184 | 0.4791 | 0.4509 | 0.4791 | 0.6922 |
|
| 144 |
+
| No log | 1.9787 | 186 | 0.4859 | 0.4643 | 0.4859 | 0.6970 |
|
| 145 |
+
| No log | 2.0 | 188 | 0.4916 | 0.4921 | 0.4916 | 0.7011 |
|
| 146 |
+
| No log | 2.0213 | 190 | 0.5040 | 0.5278 | 0.5040 | 0.7099 |
|
| 147 |
+
| No log | 2.0426 | 192 | 0.4947 | 0.5283 | 0.4947 | 0.7034 |
|
| 148 |
+
| No log | 2.0638 | 194 | 0.4736 | 0.5391 | 0.4736 | 0.6882 |
|
| 149 |
+
| No log | 2.0851 | 196 | 0.4618 | 0.4665 | 0.4618 | 0.6796 |
|
| 150 |
+
| No log | 2.1064 | 198 | 0.4611 | 0.4778 | 0.4611 | 0.6790 |
|
| 151 |
+
| No log | 2.1277 | 200 | 0.4483 | 0.5074 | 0.4483 | 0.6696 |
|
| 152 |
+
| No log | 2.1489 | 202 | 0.4489 | 0.5480 | 0.4489 | 0.6700 |
|
| 153 |
+
| No log | 2.1702 | 204 | 0.4656 | 0.5593 | 0.4656 | 0.6823 |
|
| 154 |
+
| No log | 2.1915 | 206 | 0.4482 | 0.5474 | 0.4482 | 0.6695 |
|
| 155 |
+
| No log | 2.2128 | 208 | 0.4487 | 0.5227 | 0.4487 | 0.6699 |
|
| 156 |
+
| No log | 2.2340 | 210 | 0.5469 | 0.4400 | 0.5469 | 0.7395 |
|
| 157 |
+
| No log | 2.2553 | 212 | 0.7247 | 0.3853 | 0.7247 | 0.8513 |
|
| 158 |
+
| No log | 2.2766 | 214 | 0.6856 | 0.3684 | 0.6856 | 0.8280 |
|
| 159 |
+
| No log | 2.2979 | 216 | 0.5270 | 0.3905 | 0.5270 | 0.7259 |
|
| 160 |
+
| No log | 2.3191 | 218 | 0.4537 | 0.4889 | 0.4537 | 0.6736 |
|
| 161 |
+
| No log | 2.3404 | 220 | 0.4555 | 0.5166 | 0.4555 | 0.6749 |
|
| 162 |
+
| No log | 2.3617 | 222 | 0.4364 | 0.5333 | 0.4364 | 0.6606 |
|
| 163 |
+
| No log | 2.3830 | 224 | 0.4357 | 0.5555 | 0.4357 | 0.6600 |
|
| 164 |
+
| No log | 2.4043 | 226 | 0.5339 | 0.5511 | 0.5339 | 0.7307 |
|
| 165 |
+
| No log | 2.4255 | 228 | 0.6457 | 0.5215 | 0.6457 | 0.8036 |
|
| 166 |
+
| No log | 2.4468 | 230 | 0.6696 | 0.5236 | 0.6696 | 0.8183 |
|
| 167 |
+
| No log | 2.4681 | 232 | 0.6229 | 0.5307 | 0.6229 | 0.7892 |
|
| 168 |
+
| No log | 2.4894 | 234 | 0.5367 | 0.5788 | 0.5367 | 0.7326 |
|
| 169 |
+
| No log | 2.5106 | 236 | 0.5040 | 0.5810 | 0.5040 | 0.7099 |
|
| 170 |
+
| No log | 2.5319 | 238 | 0.4577 | 0.5682 | 0.4577 | 0.6765 |
|
| 171 |
+
| No log | 2.5532 | 240 | 0.4783 | 0.5195 | 0.4783 | 0.6916 |
|
| 172 |
+
| No log | 2.5745 | 242 | 0.4666 | 0.4917 | 0.4666 | 0.6831 |
|
| 173 |
+
| No log | 2.5957 | 244 | 0.4885 | 0.4597 | 0.4885 | 0.6989 |
|
| 174 |
+
| No log | 2.6170 | 246 | 0.4939 | 0.4501 | 0.4939 | 0.7028 |
|
| 175 |
+
| No log | 2.6383 | 248 | 0.4492 | 0.5435 | 0.4492 | 0.6703 |
|
| 176 |
+
| No log | 2.6596 | 250 | 0.4392 | 0.5359 | 0.4392 | 0.6628 |
|
| 177 |
+
| No log | 2.6809 | 252 | 0.5860 | 0.5539 | 0.5860 | 0.7655 |
|
| 178 |
+
| No log | 2.7021 | 254 | 0.5884 | 0.5417 | 0.5884 | 0.7671 |
|
| 179 |
+
| No log | 2.7234 | 256 | 0.4743 | 0.5152 | 0.4743 | 0.6887 |
|
| 180 |
+
| No log | 2.7447 | 258 | 0.4565 | 0.5130 | 0.4565 | 0.6756 |
|
| 181 |
+
| No log | 2.7660 | 260 | 0.5037 | 0.3659 | 0.5037 | 0.7097 |
|
| 182 |
+
| No log | 2.7872 | 262 | 0.5783 | 0.2961 | 0.5783 | 0.7605 |
|
| 183 |
+
| No log | 2.8085 | 264 | 0.5960 | 0.3071 | 0.5960 | 0.7720 |
|
| 184 |
+
| No log | 2.8298 | 266 | 0.5651 | 0.3744 | 0.5651 | 0.7517 |
|
| 185 |
+
| No log | 2.8511 | 268 | 0.4834 | 0.5467 | 0.4834 | 0.6952 |
|
| 186 |
+
| No log | 2.8723 | 270 | 0.4120 | 0.6208 | 0.4120 | 0.6418 |
|
| 187 |
+
| No log | 2.8936 | 272 | 0.4382 | 0.6142 | 0.4382 | 0.6620 |
|
| 188 |
+
| No log | 2.9149 | 274 | 0.4525 | 0.6080 | 0.4525 | 0.6727 |
|
| 189 |
+
| No log | 2.9362 | 276 | 0.4681 | 0.6217 | 0.4681 | 0.6841 |
|
| 190 |
+
| No log | 2.9574 | 278 | 0.5913 | 0.5677 | 0.5913 | 0.7689 |
|
| 191 |
+
| No log | 2.9787 | 280 | 0.6915 | 0.4377 | 0.6915 | 0.8316 |
|
| 192 |
+
| No log | 3.0 | 282 | 0.8460 | 0.3413 | 0.8460 | 0.9198 |
|
| 193 |
+
| No log | 3.0213 | 284 | 0.8891 | 0.2589 | 0.8891 | 0.9429 |
|
| 194 |
+
| No log | 3.0426 | 286 | 0.7502 | 0.3368 | 0.7502 | 0.8662 |
|
| 195 |
+
| No log | 3.0638 | 288 | 0.5640 | 0.4077 | 0.5640 | 0.7510 |
|
| 196 |
+
| No log | 3.0851 | 290 | 0.6634 | 0.3049 | 0.6634 | 0.8145 |
|
| 197 |
+
| No log | 3.1064 | 292 | 0.6560 | 0.3207 | 0.6560 | 0.8099 |
|
| 198 |
+
| No log | 3.1277 | 294 | 0.5246 | 0.5175 | 0.5246 | 0.7243 |
|
| 199 |
+
| No log | 3.1489 | 296 | 0.4454 | 0.5169 | 0.4454 | 0.6674 |
|
| 200 |
+
| No log | 3.1702 | 298 | 0.4860 | 0.4285 | 0.4860 | 0.6971 |
|
| 201 |
+
| No log | 3.1915 | 300 | 0.5543 | 0.5088 | 0.5543 | 0.7445 |
|
| 202 |
+
| No log | 3.2128 | 302 | 0.5703 | 0.5592 | 0.5703 | 0.7552 |
|
| 203 |
+
| No log | 3.2340 | 304 | 0.6814 | 0.5316 | 0.6814 | 0.8255 |
|
| 204 |
+
| No log | 3.2553 | 306 | 0.5497 | 0.5704 | 0.5497 | 0.7414 |
|
| 205 |
+
| No log | 3.2766 | 308 | 0.4852 | 0.5788 | 0.4852 | 0.6966 |
|
| 206 |
+
| No log | 3.2979 | 310 | 0.4808 | 0.5853 | 0.4808 | 0.6934 |
|
| 207 |
+
| No log | 3.3191 | 312 | 0.4876 | 0.6232 | 0.4876 | 0.6983 |
|
| 208 |
+
| No log | 3.3404 | 314 | 0.4442 | 0.5722 | 0.4442 | 0.6665 |
|
| 209 |
+
| No log | 3.3617 | 316 | 0.4602 | 0.5201 | 0.4602 | 0.6784 |
|
| 210 |
+
| No log | 3.3830 | 318 | 0.5018 | 0.4900 | 0.5018 | 0.7084 |
|
| 211 |
+
| No log | 3.4043 | 320 | 0.4665 | 0.5059 | 0.4665 | 0.6830 |
|
| 212 |
+
| No log | 3.4255 | 322 | 0.4330 | 0.5721 | 0.4330 | 0.6580 |
|
| 213 |
+
| No log | 3.4468 | 324 | 0.4265 | 0.5661 | 0.4265 | 0.6531 |
|
| 214 |
+
| No log | 3.4681 | 326 | 0.4309 | 0.5708 | 0.4309 | 0.6565 |
|
| 215 |
+
| No log | 3.4894 | 328 | 0.4452 | 0.5651 | 0.4452 | 0.6672 |
|
| 216 |
+
| No log | 3.5106 | 330 | 0.4438 | 0.5648 | 0.4438 | 0.6662 |
|
| 217 |
+
| No log | 3.5319 | 332 | 0.4198 | 0.5478 | 0.4198 | 0.6479 |
|
| 218 |
+
| No log | 3.5532 | 334 | 0.4053 | 0.5411 | 0.4053 | 0.6366 |
|
| 219 |
+
| No log | 3.5745 | 336 | 0.4120 | 0.5259 | 0.4120 | 0.6419 |
|
| 220 |
+
| No log | 3.5957 | 338 | 0.4094 | 0.5385 | 0.4094 | 0.6398 |
|
| 221 |
+
| No log | 3.6170 | 340 | 0.4232 | 0.5686 | 0.4232 | 0.6505 |
|
| 222 |
+
| No log | 3.6383 | 342 | 0.4051 | 0.5656 | 0.4051 | 0.6365 |
|
| 223 |
+
| No log | 3.6596 | 344 | 0.4120 | 0.5688 | 0.4120 | 0.6419 |
|
| 224 |
+
| No log | 3.6809 | 346 | 0.4502 | 0.5418 | 0.4502 | 0.6710 |
|
| 225 |
+
| No log | 3.7021 | 348 | 0.4652 | 0.5069 | 0.4652 | 0.6820 |
|
| 226 |
+
| No log | 3.7234 | 350 | 0.4670 | 0.5426 | 0.4670 | 0.6834 |
|
| 227 |
+
| No log | 3.7447 | 352 | 0.5051 | 0.5283 | 0.5051 | 0.7107 |
|
| 228 |
+
| No log | 3.7660 | 354 | 0.4791 | 0.5605 | 0.4791 | 0.6921 |
|
| 229 |
+
| No log | 3.7872 | 356 | 0.4123 | 0.5928 | 0.4123 | 0.6421 |
|
| 230 |
+
| No log | 3.8085 | 358 | 0.3877 | 0.5926 | 0.3877 | 0.6226 |
|
| 231 |
+
| No log | 3.8298 | 360 | 0.3934 | 0.5989 | 0.3934 | 0.6273 |
|
| 232 |
+
| No log | 3.8511 | 362 | 0.3935 | 0.5523 | 0.3935 | 0.6273 |
|
| 233 |
+
| No log | 3.8723 | 364 | 0.4069 | 0.5750 | 0.4069 | 0.6379 |
|
| 234 |
+
| No log | 3.8936 | 366 | 0.4524 | 0.5934 | 0.4524 | 0.6726 |
|
| 235 |
+
| No log | 3.9149 | 368 | 0.5945 | 0.5394 | 0.5945 | 0.7711 |
|
| 236 |
+
| No log | 3.9362 | 370 | 0.6755 | 0.5534 | 0.6755 | 0.8219 |
|
| 237 |
+
| No log | 3.9574 | 372 | 0.6053 | 0.5956 | 0.6053 | 0.7780 |
|
| 238 |
+
| No log | 3.9787 | 374 | 0.4928 | 0.6326 | 0.4928 | 0.7020 |
|
| 239 |
+
| No log | 4.0 | 376 | 0.4880 | 0.6508 | 0.4880 | 0.6986 |
|
| 240 |
+
| No log | 4.0213 | 378 | 0.4584 | 0.6462 | 0.4584 | 0.6771 |
|
| 241 |
+
| No log | 4.0426 | 380 | 0.4568 | 0.6149 | 0.4568 | 0.6758 |
|
| 242 |
+
| No log | 4.0638 | 382 | 0.4601 | 0.5931 | 0.4601 | 0.6783 |
|
| 243 |
+
| No log | 4.0851 | 384 | 0.4218 | 0.5833 | 0.4218 | 0.6495 |
|
| 244 |
+
| No log | 4.1064 | 386 | 0.4170 | 0.5574 | 0.4170 | 0.6458 |
|
| 245 |
+
| No log | 4.1277 | 388 | 0.4103 | 0.5575 | 0.4103 | 0.6406 |
|
| 246 |
+
| No log | 4.1489 | 390 | 0.4059 | 0.5597 | 0.4059 | 0.6371 |
|
| 247 |
+
| No log | 4.1702 | 392 | 0.4462 | 0.5944 | 0.4462 | 0.6680 |
|
| 248 |
+
| No log | 4.1915 | 394 | 0.4308 | 0.6010 | 0.4308 | 0.6563 |
|
| 249 |
+
| No log | 4.2128 | 396 | 0.4690 | 0.5524 | 0.4690 | 0.6848 |
|
| 250 |
+
| No log | 4.2340 | 398 | 0.4814 | 0.5282 | 0.4814 | 0.6938 |
|
| 251 |
+
| No log | 4.2553 | 400 | 0.5534 | 0.5092 | 0.5534 | 0.7439 |
|
| 252 |
+
| No log | 4.2766 | 402 | 0.6290 | 0.5354 | 0.6290 | 0.7931 |
|
| 253 |
+
| No log | 4.2979 | 404 | 0.6553 | 0.5475 | 0.6553 | 0.8095 |
|
| 254 |
+
| No log | 4.3191 | 406 | 0.5146 | 0.6036 | 0.5146 | 0.7174 |
|
| 255 |
+
| No log | 4.3404 | 408 | 0.5226 | 0.6054 | 0.5226 | 0.7229 |
|
| 256 |
+
| No log | 4.3617 | 410 | 0.6431 | 0.5968 | 0.6431 | 0.8020 |
|
| 257 |
+
| No log | 4.3830 | 412 | 0.6137 | 0.5980 | 0.6137 | 0.7834 |
|
| 258 |
+
| No log | 4.4043 | 414 | 0.6730 | 0.5499 | 0.6730 | 0.8204 |
|
| 259 |
+
| No log | 4.4255 | 416 | 0.5656 | 0.5738 | 0.5656 | 0.7521 |
|
| 260 |
+
| No log | 4.4468 | 418 | 0.4316 | 0.6334 | 0.4316 | 0.6570 |
|
| 261 |
+
| No log | 4.4681 | 420 | 0.4480 | 0.5767 | 0.4480 | 0.6693 |
|
| 262 |
+
| No log | 4.4894 | 422 | 0.4281 | 0.5523 | 0.4281 | 0.6543 |
|
| 263 |
+
| No log | 4.5106 | 424 | 0.4249 | 0.5525 | 0.4249 | 0.6518 |
|
| 264 |
+
| No log | 4.5319 | 426 | 0.4029 | 0.5712 | 0.4029 | 0.6348 |
|
| 265 |
+
| No log | 4.5532 | 428 | 0.4092 | 0.6486 | 0.4092 | 0.6397 |
|
| 266 |
+
| No log | 4.5745 | 430 | 0.4363 | 0.6061 | 0.4363 | 0.6606 |
|
| 267 |
+
| No log | 4.5957 | 432 | 0.4401 | 0.5857 | 0.4401 | 0.6634 |
|
| 268 |
+
| No log | 4.6170 | 434 | 0.4174 | 0.6027 | 0.4174 | 0.6460 |
|
| 269 |
+
| No log | 4.6383 | 436 | 0.4183 | 0.5956 | 0.4183 | 0.6467 |
|
| 270 |
+
| No log | 4.6596 | 438 | 0.3976 | 0.6053 | 0.3976 | 0.6305 |
|
| 271 |
+
| No log | 4.6809 | 440 | 0.4289 | 0.6319 | 0.4289 | 0.6549 |
|
| 272 |
+
| No log | 4.7021 | 442 | 0.5079 | 0.6080 | 0.5079 | 0.7126 |
|
| 273 |
+
| No log | 4.7234 | 444 | 0.5477 | 0.5795 | 0.5477 | 0.7401 |
|
| 274 |
+
| No log | 4.7447 | 446 | 0.5512 | 0.5918 | 0.5512 | 0.7424 |
|
| 275 |
+
| No log | 4.7660 | 448 | 0.5499 | 0.6019 | 0.5499 | 0.7415 |
|
| 276 |
+
| No log | 4.7872 | 450 | 0.4962 | 0.5989 | 0.4962 | 0.7044 |
|
| 277 |
+
| No log | 4.8085 | 452 | 0.4837 | 0.6148 | 0.4837 | 0.6955 |
|
| 278 |
+
| No log | 4.8298 | 454 | 0.4119 | 0.6346 | 0.4119 | 0.6418 |
|
| 279 |
+
| No log | 4.8511 | 456 | 0.4047 | 0.5990 | 0.4047 | 0.6362 |
|
| 280 |
+
| No log | 4.8723 | 458 | 0.4108 | 0.5605 | 0.4108 | 0.6409 |
|
| 281 |
+
| No log | 4.8936 | 460 | 0.4426 | 0.4997 | 0.4426 | 0.6653 |
|
| 282 |
+
| No log | 4.9149 | 462 | 0.5077 | 0.4524 | 0.5077 | 0.7125 |
|
| 283 |
+
| No log | 4.9362 | 464 | 0.4933 | 0.5046 | 0.4933 | 0.7024 |
|
| 284 |
+
| No log | 4.9574 | 466 | 0.4723 | 0.5452 | 0.4723 | 0.6872 |
|
| 285 |
+
| No log | 4.9787 | 468 | 0.4308 | 0.5926 | 0.4308 | 0.6564 |
|
| 286 |
+
| No log | 5.0 | 470 | 0.4272 | 0.5785 | 0.4272 | 0.6536 |
|
| 287 |
+
| No log | 5.0213 | 472 | 0.4132 | 0.5911 | 0.4132 | 0.6428 |
|
| 288 |
+
| No log | 5.0426 | 474 | 0.4730 | 0.6206 | 0.4730 | 0.6877 |
|
| 289 |
+
| No log | 5.0638 | 476 | 0.5411 | 0.5917 | 0.5411 | 0.7356 |
|
| 290 |
+
| No log | 5.0851 | 478 | 0.4614 | 0.6025 | 0.4614 | 0.6792 |
|
| 291 |
+
| No log | 5.1064 | 480 | 0.4207 | 0.5840 | 0.4207 | 0.6486 |
|
| 292 |
+
| No log | 5.1277 | 482 | 0.4282 | 0.5737 | 0.4282 | 0.6544 |
|
| 293 |
+
| No log | 5.1489 | 484 | 0.5156 | 0.5876 | 0.5156 | 0.7181 |
|
| 294 |
+
| No log | 5.1702 | 486 | 0.5548 | 0.5716 | 0.5548 | 0.7448 |
|
| 295 |
+
| No log | 5.1915 | 488 | 0.4640 | 0.6395 | 0.4640 | 0.6812 |
|
| 296 |
+
| No log | 5.2128 | 490 | 0.4520 | 0.6008 | 0.4520 | 0.6723 |
|
| 297 |
+
| No log | 5.2340 | 492 | 0.4696 | 0.6422 | 0.4696 | 0.6852 |
|
| 298 |
+
| No log | 5.2553 | 494 | 0.5115 | 0.6101 | 0.5115 | 0.7152 |
|
| 299 |
+
| No log | 5.2766 | 496 | 0.5953 | 0.5710 | 0.5953 | 0.7716 |
|
| 300 |
+
| No log | 5.2979 | 498 | 0.5338 | 0.6147 | 0.5338 | 0.7306 |
|
| 301 |
+
| 0.4408 | 5.3191 | 500 | 0.4227 | 0.5767 | 0.4227 | 0.6502 |
|
| 302 |
+
| 0.4408 | 5.3404 | 502 | 0.4154 | 0.5858 | 0.4154 | 0.6445 |
|
| 303 |
+
| 0.4408 | 5.3617 | 504 | 0.4910 | 0.6080 | 0.4910 | 0.7007 |
|
| 304 |
+
| 0.4408 | 5.3830 | 506 | 0.6428 | 0.5427 | 0.6428 | 0.8017 |
|
| 305 |
+
| 0.4408 | 5.4043 | 508 | 0.5662 | 0.5934 | 0.5662 | 0.7525 |
|
| 306 |
+
| 0.4408 | 5.4255 | 510 | 0.4544 | 0.6087 | 0.4544 | 0.6741 |
|
| 307 |
+
| 0.4408 | 5.4468 | 512 | 0.4561 | 0.5974 | 0.4561 | 0.6753 |
|
| 308 |
+
| 0.4408 | 5.4681 | 514 | 0.5265 | 0.5743 | 0.5265 | 0.7256 |
|
| 309 |
+
| 0.4408 | 5.4894 | 516 | 0.6612 | 0.5555 | 0.6612 | 0.8131 |
|
| 310 |
+
| 0.4408 | 5.5106 | 518 | 0.5593 | 0.6011 | 0.5593 | 0.7479 |
|
| 311 |
+
| 0.4408 | 5.5319 | 520 | 0.4783 | 0.6292 | 0.4783 | 0.6916 |
|
| 312 |
+
| 0.4408 | 5.5532 | 522 | 0.4702 | 0.5976 | 0.4702 | 0.6857 |
|
| 313 |
+
| 0.4408 | 5.5745 | 524 | 0.4426 | 0.6160 | 0.4426 | 0.6653 |
|
| 314 |
+
| 0.4408 | 5.5957 | 526 | 0.4581 | 0.6378 | 0.4581 | 0.6769 |
|
| 315 |
+
| 0.4408 | 5.6170 | 528 | 0.5307 | 0.5955 | 0.5307 | 0.7285 |
|
| 316 |
+
| 0.4408 | 5.6383 | 530 | 0.5133 | 0.6090 | 0.5133 | 0.7164 |
|
| 317 |
+
| 0.4408 | 5.6596 | 532 | 0.4372 | 0.6279 | 0.4372 | 0.6612 |
|
| 318 |
+
| 0.4408 | 5.6809 | 534 | 0.4346 | 0.6228 | 0.4346 | 0.6592 |
|
| 319 |
+
| 0.4408 | 5.7021 | 536 | 0.4987 | 0.5880 | 0.4987 | 0.7062 |
|
| 320 |
+
| 0.4408 | 5.7234 | 538 | 0.6290 | 0.5233 | 0.6290 | 0.7931 |
|
| 321 |
+
| 0.4408 | 5.7447 | 540 | 0.5660 | 0.5294 | 0.5660 | 0.7523 |
|
| 322 |
+
| 0.4408 | 5.7660 | 542 | 0.4648 | 0.6267 | 0.4648 | 0.6818 |
|
| 323 |
+
| 0.4408 | 5.7872 | 544 | 0.4184 | 0.6184 | 0.4184 | 0.6468 |
|
| 324 |
+
| 0.4408 | 5.8085 | 546 | 0.4122 | 0.6284 | 0.4122 | 0.6420 |
|
| 325 |
+
| 0.4408 | 5.8298 | 548 | 0.4384 | 0.6273 | 0.4384 | 0.6621 |
|
| 326 |
+
| 0.4408 | 5.8511 | 550 | 0.5868 | 0.5337 | 0.5868 | 0.7660 |
|
| 327 |
+
| 0.4408 | 5.8723 | 552 | 0.7145 | 0.5199 | 0.7145 | 0.8453 |
|
| 328 |
+
| 0.4408 | 5.8936 | 554 | 0.5561 | 0.5821 | 0.5561 | 0.7457 |
|
| 329 |
+
| 0.4408 | 5.9149 | 556 | 0.4488 | 0.6387 | 0.4488 | 0.6700 |
|
| 330 |
+
| 0.4408 | 5.9362 | 558 | 0.4575 | 0.6300 | 0.4575 | 0.6764 |
|
| 331 |
+
| 0.4408 | 5.9574 | 560 | 0.5166 | 0.6150 | 0.5166 | 0.7188 |
|
| 332 |
+
| 0.4408 | 5.9787 | 562 | 0.7070 | 0.5283 | 0.7070 | 0.8408 |
|
| 333 |
+
| 0.4408 | 6.0 | 564 | 0.6845 | 0.5256 | 0.6845 | 0.8273 |
|
| 334 |
+
| 0.4408 | 6.0213 | 566 | 0.4975 | 0.5945 | 0.4975 | 0.7054 |
|
| 335 |
+
| 0.4408 | 6.0426 | 568 | 0.4445 | 0.5716 | 0.4445 | 0.6667 |
|
| 336 |
+
| 0.4408 | 6.0638 | 570 | 0.4293 | 0.5760 | 0.4293 | 0.6552 |
|
| 337 |
+
| 0.4408 | 6.0851 | 572 | 0.4427 | 0.6201 | 0.4427 | 0.6653 |
|
| 338 |
+
| 0.4408 | 6.1064 | 574 | 0.5550 | 0.5536 | 0.5550 | 0.7450 |
|
| 339 |
+
| 0.4408 | 6.1277 | 576 | 0.5314 | 0.5714 | 0.5314 | 0.7290 |
|
| 340 |
+
| 0.4408 | 6.1489 | 578 | 0.4474 | 0.5914 | 0.4474 | 0.6689 |
|
| 341 |
+
| 0.4408 | 6.1702 | 580 | 0.4070 | 0.6072 | 0.4070 | 0.6380 |
|
| 342 |
+
| 0.4408 | 6.1915 | 582 | 0.4053 | 0.5952 | 0.4053 | 0.6366 |
|
| 343 |
+
| 0.4408 | 6.2128 | 584 | 0.4212 | 0.6040 | 0.4212 | 0.6490 |
|
| 344 |
+
| 0.4408 | 6.2340 | 586 | 0.5671 | 0.5313 | 0.5671 | 0.7531 |
|
| 345 |
+
| 0.4408 | 6.2553 | 588 | 0.6355 | 0.4988 | 0.6355 | 0.7972 |
|
| 346 |
+
| 0.4408 | 6.2766 | 590 | 0.5195 | 0.5689 | 0.5195 | 0.7208 |
|
| 347 |
+
| 0.4408 | 6.2979 | 592 | 0.4083 | 0.5654 | 0.4083 | 0.6390 |
|
| 348 |
+
| 0.4408 | 6.3191 | 594 | 0.4088 | 0.5376 | 0.4088 | 0.6394 |
|
| 349 |
+
|
| 350 |
+
|
| 351 |
+
### Framework versions
|
| 352 |
+
|
| 353 |
+
- Transformers 4.44.2
|
| 354 |
+
- Pytorch 2.4.0+cu118
|
| 355 |
+
- Datasets 2.21.0
|
| 356 |
+
- 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:c9d709dd5ef7dc086ddfcffccd92eadbdbd879efd34186fc3917aa76ec6097ef
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f05df75a5bda3cd30f879006a0f1bdcdac99cac6f73a11dd7d5dcc4cf4ebea58
|
| 3 |
+
size 5240
|