Training in progress, step 500
Browse files- README.md +365 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,365 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_TestTask6_style
|
| 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_TestTask6_style
|
| 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: 0.6625
|
| 19 |
+
- Qwk: 0.5624
|
| 20 |
+
- Mse: 0.6625
|
| 21 |
+
- Rmse: 0.8139
|
| 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 | 0.0194 | 2 | 4.2549 | -0.0101 | 4.2549 | 2.0627 |
|
| 53 |
+
| No log | 0.0388 | 4 | 2.4120 | 0.0821 | 2.4120 | 1.5531 |
|
| 54 |
+
| No log | 0.0583 | 6 | 1.1621 | 0.0141 | 1.1621 | 1.0780 |
|
| 55 |
+
| No log | 0.0777 | 8 | 0.7408 | 0.1705 | 0.7408 | 0.8607 |
|
| 56 |
+
| No log | 0.0971 | 10 | 0.6591 | 0.1659 | 0.6591 | 0.8118 |
|
| 57 |
+
| No log | 0.1165 | 12 | 0.6962 | 0.1637 | 0.6962 | 0.8344 |
|
| 58 |
+
| No log | 0.1359 | 14 | 0.7775 | 0.2388 | 0.7775 | 0.8818 |
|
| 59 |
+
| No log | 0.1553 | 16 | 0.7043 | 0.2659 | 0.7043 | 0.8392 |
|
| 60 |
+
| No log | 0.1748 | 18 | 0.7042 | 0.3202 | 0.7042 | 0.8392 |
|
| 61 |
+
| No log | 0.1942 | 20 | 1.2381 | 0.1429 | 1.2381 | 1.1127 |
|
| 62 |
+
| No log | 0.2136 | 22 | 1.1243 | 0.1606 | 1.1243 | 1.0604 |
|
| 63 |
+
| No log | 0.2330 | 24 | 0.6687 | 0.3300 | 0.6687 | 0.8178 |
|
| 64 |
+
| No log | 0.2524 | 26 | 0.5224 | 0.4248 | 0.5224 | 0.7228 |
|
| 65 |
+
| No log | 0.2718 | 28 | 0.5669 | 0.3243 | 0.5669 | 0.7529 |
|
| 66 |
+
| No log | 0.2913 | 30 | 0.5316 | 0.3743 | 0.5316 | 0.7291 |
|
| 67 |
+
| No log | 0.3107 | 32 | 0.5229 | 0.4262 | 0.5229 | 0.7231 |
|
| 68 |
+
| No log | 0.3301 | 34 | 0.5856 | 0.4064 | 0.5856 | 0.7653 |
|
| 69 |
+
| No log | 0.3495 | 36 | 0.8114 | 0.2506 | 0.8114 | 0.9008 |
|
| 70 |
+
| No log | 0.3689 | 38 | 0.8782 | 0.2470 | 0.8782 | 0.9371 |
|
| 71 |
+
| No log | 0.3883 | 40 | 0.6566 | 0.3774 | 0.6566 | 0.8103 |
|
| 72 |
+
| No log | 0.4078 | 42 | 0.5460 | 0.4424 | 0.5460 | 0.7389 |
|
| 73 |
+
| No log | 0.4272 | 44 | 0.6044 | 0.4215 | 0.6044 | 0.7774 |
|
| 74 |
+
| No log | 0.4466 | 46 | 0.6085 | 0.3842 | 0.6085 | 0.7800 |
|
| 75 |
+
| No log | 0.4660 | 48 | 0.5538 | 0.4453 | 0.5538 | 0.7442 |
|
| 76 |
+
| No log | 0.4854 | 50 | 0.5461 | 0.4785 | 0.5461 | 0.7390 |
|
| 77 |
+
| No log | 0.5049 | 52 | 0.6209 | 0.5048 | 0.6209 | 0.7880 |
|
| 78 |
+
| No log | 0.5243 | 54 | 0.7296 | 0.4396 | 0.7296 | 0.8542 |
|
| 79 |
+
| No log | 0.5437 | 56 | 0.6276 | 0.4755 | 0.6276 | 0.7922 |
|
| 80 |
+
| No log | 0.5631 | 58 | 0.4761 | 0.5686 | 0.4761 | 0.6900 |
|
| 81 |
+
| No log | 0.5825 | 60 | 0.4837 | 0.4984 | 0.4837 | 0.6955 |
|
| 82 |
+
| No log | 0.6019 | 62 | 0.6290 | 0.4140 | 0.6290 | 0.7931 |
|
| 83 |
+
| No log | 0.6214 | 64 | 0.8484 | 0.3305 | 0.8484 | 0.9211 |
|
| 84 |
+
| No log | 0.6408 | 66 | 0.9097 | 0.3165 | 0.9097 | 0.9538 |
|
| 85 |
+
| No log | 0.6602 | 68 | 0.7720 | 0.3892 | 0.7720 | 0.8786 |
|
| 86 |
+
| No log | 0.6796 | 70 | 0.5227 | 0.5091 | 0.5227 | 0.7230 |
|
| 87 |
+
| No log | 0.6990 | 72 | 0.4428 | 0.5102 | 0.4428 | 0.6655 |
|
| 88 |
+
| No log | 0.7184 | 74 | 0.4933 | 0.5723 | 0.4933 | 0.7023 |
|
| 89 |
+
| No log | 0.7379 | 76 | 0.5711 | 0.5314 | 0.5711 | 0.7557 |
|
| 90 |
+
| No log | 0.7573 | 78 | 0.5017 | 0.5627 | 0.5017 | 0.7083 |
|
| 91 |
+
| No log | 0.7767 | 80 | 0.4849 | 0.5821 | 0.4849 | 0.6964 |
|
| 92 |
+
| No log | 0.7961 | 82 | 0.4577 | 0.5968 | 0.4577 | 0.6765 |
|
| 93 |
+
| No log | 0.8155 | 84 | 0.4395 | 0.5729 | 0.4395 | 0.6630 |
|
| 94 |
+
| No log | 0.8350 | 86 | 0.4426 | 0.5979 | 0.4426 | 0.6653 |
|
| 95 |
+
| No log | 0.8544 | 88 | 0.4610 | 0.5776 | 0.4610 | 0.6790 |
|
| 96 |
+
| No log | 0.8738 | 90 | 0.5515 | 0.5409 | 0.5515 | 0.7426 |
|
| 97 |
+
| No log | 0.8932 | 92 | 0.6211 | 0.5724 | 0.6211 | 0.7881 |
|
| 98 |
+
| No log | 0.9126 | 94 | 0.7063 | 0.5468 | 0.7063 | 0.8404 |
|
| 99 |
+
| No log | 0.9320 | 96 | 0.7522 | 0.5229 | 0.7522 | 0.8673 |
|
| 100 |
+
| No log | 0.9515 | 98 | 0.7174 | 0.5726 | 0.7174 | 0.8470 |
|
| 101 |
+
| No log | 0.9709 | 100 | 0.6388 | 0.5634 | 0.6388 | 0.7993 |
|
| 102 |
+
| No log | 0.9903 | 102 | 0.5195 | 0.5904 | 0.5195 | 0.7208 |
|
| 103 |
+
| No log | 1.0097 | 104 | 0.4184 | 0.6514 | 0.4184 | 0.6468 |
|
| 104 |
+
| No log | 1.0291 | 106 | 0.3865 | 0.6491 | 0.3865 | 0.6217 |
|
| 105 |
+
| No log | 1.0485 | 108 | 0.3816 | 0.6594 | 0.3816 | 0.6177 |
|
| 106 |
+
| No log | 1.0680 | 110 | 0.3951 | 0.6475 | 0.3951 | 0.6286 |
|
| 107 |
+
| No log | 1.0874 | 112 | 0.4142 | 0.6382 | 0.4142 | 0.6436 |
|
| 108 |
+
| No log | 1.1068 | 114 | 0.4241 | 0.6543 | 0.4241 | 0.6512 |
|
| 109 |
+
| No log | 1.1262 | 116 | 0.4117 | 0.6665 | 0.4117 | 0.6416 |
|
| 110 |
+
| No log | 1.1456 | 118 | 0.4581 | 0.6687 | 0.4581 | 0.6768 |
|
| 111 |
+
| No log | 1.1650 | 120 | 0.6624 | 0.5581 | 0.6624 | 0.8139 |
|
| 112 |
+
| No log | 1.1845 | 122 | 0.7322 | 0.5348 | 0.7322 | 0.8557 |
|
| 113 |
+
| No log | 1.2039 | 124 | 0.5770 | 0.5847 | 0.5770 | 0.7596 |
|
| 114 |
+
| No log | 1.2233 | 126 | 0.4728 | 0.6376 | 0.4728 | 0.6876 |
|
| 115 |
+
| No log | 1.2427 | 128 | 0.4770 | 0.6192 | 0.4770 | 0.6906 |
|
| 116 |
+
| No log | 1.2621 | 130 | 0.4355 | 0.6288 | 0.4355 | 0.6599 |
|
| 117 |
+
| No log | 1.2816 | 132 | 0.3931 | 0.6534 | 0.3931 | 0.6270 |
|
| 118 |
+
| No log | 1.3010 | 134 | 0.5050 | 0.6200 | 0.5050 | 0.7107 |
|
| 119 |
+
| No log | 1.3204 | 136 | 0.6473 | 0.5240 | 0.6473 | 0.8046 |
|
| 120 |
+
| No log | 1.3398 | 138 | 0.5956 | 0.4820 | 0.5956 | 0.7717 |
|
| 121 |
+
| No log | 1.3592 | 140 | 0.5373 | 0.4899 | 0.5373 | 0.7330 |
|
| 122 |
+
| No log | 1.3786 | 142 | 0.4496 | 0.5462 | 0.4496 | 0.6706 |
|
| 123 |
+
| No log | 1.3981 | 144 | 0.4266 | 0.6052 | 0.4266 | 0.6531 |
|
| 124 |
+
| No log | 1.4175 | 146 | 0.4478 | 0.6070 | 0.4478 | 0.6692 |
|
| 125 |
+
| No log | 1.4369 | 148 | 0.4870 | 0.5996 | 0.4870 | 0.6979 |
|
| 126 |
+
| No log | 1.4563 | 150 | 0.5452 | 0.5547 | 0.5452 | 0.7384 |
|
| 127 |
+
| No log | 1.4757 | 152 | 0.4972 | 0.5891 | 0.4972 | 0.7051 |
|
| 128 |
+
| No log | 1.4951 | 154 | 0.4275 | 0.6196 | 0.4275 | 0.6538 |
|
| 129 |
+
| No log | 1.5146 | 156 | 0.4839 | 0.6210 | 0.4839 | 0.6956 |
|
| 130 |
+
| No log | 1.5340 | 158 | 0.6324 | 0.5156 | 0.6324 | 0.7952 |
|
| 131 |
+
| No log | 1.5534 | 160 | 0.6910 | 0.5288 | 0.6910 | 0.8312 |
|
| 132 |
+
| No log | 1.5728 | 162 | 0.6412 | 0.5672 | 0.6412 | 0.8007 |
|
| 133 |
+
| No log | 1.5922 | 164 | 0.5695 | 0.5466 | 0.5695 | 0.7547 |
|
| 134 |
+
| No log | 1.6117 | 166 | 0.5487 | 0.5667 | 0.5487 | 0.7407 |
|
| 135 |
+
| No log | 1.6311 | 168 | 0.5396 | 0.5715 | 0.5396 | 0.7346 |
|
| 136 |
+
| No log | 1.6505 | 170 | 0.4522 | 0.5918 | 0.4522 | 0.6725 |
|
| 137 |
+
| No log | 1.6699 | 172 | 0.3959 | 0.6105 | 0.3959 | 0.6292 |
|
| 138 |
+
| No log | 1.6893 | 174 | 0.4072 | 0.5413 | 0.4072 | 0.6381 |
|
| 139 |
+
| No log | 1.7087 | 176 | 0.4149 | 0.5463 | 0.4149 | 0.6441 |
|
| 140 |
+
| No log | 1.7282 | 178 | 0.4222 | 0.5923 | 0.4222 | 0.6498 |
|
| 141 |
+
| No log | 1.7476 | 180 | 0.4433 | 0.6076 | 0.4433 | 0.6658 |
|
| 142 |
+
| No log | 1.7670 | 182 | 0.4928 | 0.5847 | 0.4928 | 0.7020 |
|
| 143 |
+
| No log | 1.7864 | 184 | 0.5300 | 0.5679 | 0.5300 | 0.7280 |
|
| 144 |
+
| No log | 1.8058 | 186 | 0.5408 | 0.5854 | 0.5408 | 0.7354 |
|
| 145 |
+
| No log | 1.8252 | 188 | 0.6806 | 0.5383 | 0.6806 | 0.8250 |
|
| 146 |
+
| No log | 1.8447 | 190 | 0.7199 | 0.5188 | 0.7199 | 0.8485 |
|
| 147 |
+
| No log | 1.8641 | 192 | 0.6166 | 0.5630 | 0.6166 | 0.7853 |
|
| 148 |
+
| No log | 1.8835 | 194 | 0.5421 | 0.5971 | 0.5421 | 0.7363 |
|
| 149 |
+
| No log | 1.9029 | 196 | 0.4481 | 0.6090 | 0.4481 | 0.6694 |
|
| 150 |
+
| No log | 1.9223 | 198 | 0.4094 | 0.6610 | 0.4094 | 0.6398 |
|
| 151 |
+
| No log | 1.9417 | 200 | 0.3989 | 0.6321 | 0.3989 | 0.6316 |
|
| 152 |
+
| No log | 1.9612 | 202 | 0.4367 | 0.6084 | 0.4367 | 0.6608 |
|
| 153 |
+
| No log | 1.9806 | 204 | 0.5659 | 0.5643 | 0.5659 | 0.7523 |
|
| 154 |
+
| No log | 2.0 | 206 | 0.6567 | 0.5469 | 0.6567 | 0.8104 |
|
| 155 |
+
| No log | 2.0194 | 208 | 0.5817 | 0.5684 | 0.5817 | 0.7627 |
|
| 156 |
+
| No log | 2.0388 | 210 | 0.4794 | 0.5682 | 0.4794 | 0.6924 |
|
| 157 |
+
| No log | 2.0583 | 212 | 0.5466 | 0.5478 | 0.5466 | 0.7393 |
|
| 158 |
+
| No log | 2.0777 | 214 | 0.6550 | 0.4778 | 0.6550 | 0.8093 |
|
| 159 |
+
| No log | 2.0971 | 216 | 0.7004 | 0.4765 | 0.7004 | 0.8369 |
|
| 160 |
+
| No log | 2.1165 | 218 | 0.6442 | 0.5157 | 0.6442 | 0.8026 |
|
| 161 |
+
| No log | 2.1359 | 220 | 0.5243 | 0.5495 | 0.5243 | 0.7241 |
|
| 162 |
+
| No log | 2.1553 | 222 | 0.4555 | 0.6434 | 0.4555 | 0.6749 |
|
| 163 |
+
| No log | 2.1748 | 224 | 0.4800 | 0.6099 | 0.4800 | 0.6928 |
|
| 164 |
+
| No log | 2.1942 | 226 | 0.4896 | 0.6223 | 0.4896 | 0.6997 |
|
| 165 |
+
| No log | 2.2136 | 228 | 0.4845 | 0.6259 | 0.4845 | 0.6960 |
|
| 166 |
+
| No log | 2.2330 | 230 | 0.5370 | 0.5712 | 0.5370 | 0.7328 |
|
| 167 |
+
| No log | 2.2524 | 232 | 0.5853 | 0.5475 | 0.5853 | 0.7651 |
|
| 168 |
+
| No log | 2.2718 | 234 | 0.5995 | 0.5022 | 0.5995 | 0.7743 |
|
| 169 |
+
| No log | 2.2913 | 236 | 0.5423 | 0.5419 | 0.5423 | 0.7364 |
|
| 170 |
+
| No log | 2.3107 | 238 | 0.4821 | 0.6222 | 0.4821 | 0.6944 |
|
| 171 |
+
| No log | 2.3301 | 240 | 0.4659 | 0.6513 | 0.4659 | 0.6825 |
|
| 172 |
+
| No log | 2.3495 | 242 | 0.5100 | 0.5872 | 0.5100 | 0.7142 |
|
| 173 |
+
| No log | 2.3689 | 244 | 0.4915 | 0.5851 | 0.4915 | 0.7011 |
|
| 174 |
+
| No log | 2.3883 | 246 | 0.4543 | 0.6368 | 0.4543 | 0.6740 |
|
| 175 |
+
| No log | 2.4078 | 248 | 0.4374 | 0.6110 | 0.4374 | 0.6613 |
|
| 176 |
+
| No log | 2.4272 | 250 | 0.4627 | 0.5803 | 0.4627 | 0.6802 |
|
| 177 |
+
| No log | 2.4466 | 252 | 0.4809 | 0.5667 | 0.4809 | 0.6935 |
|
| 178 |
+
| No log | 2.4660 | 254 | 0.5564 | 0.5106 | 0.5564 | 0.7459 |
|
| 179 |
+
| No log | 2.4854 | 256 | 0.6645 | 0.4774 | 0.6645 | 0.8152 |
|
| 180 |
+
| No log | 2.5049 | 258 | 0.6290 | 0.5079 | 0.6290 | 0.7931 |
|
| 181 |
+
| No log | 2.5243 | 260 | 0.4964 | 0.5556 | 0.4964 | 0.7046 |
|
| 182 |
+
| No log | 2.5437 | 262 | 0.4947 | 0.5873 | 0.4947 | 0.7033 |
|
| 183 |
+
| No log | 2.5631 | 264 | 0.5097 | 0.5622 | 0.5097 | 0.7139 |
|
| 184 |
+
| No log | 2.5825 | 266 | 0.4607 | 0.6322 | 0.4607 | 0.6787 |
|
| 185 |
+
| No log | 2.6019 | 268 | 0.4607 | 0.5844 | 0.4607 | 0.6787 |
|
| 186 |
+
| No log | 2.6214 | 270 | 0.5539 | 0.5393 | 0.5539 | 0.7443 |
|
| 187 |
+
| No log | 2.6408 | 272 | 0.7170 | 0.5062 | 0.7170 | 0.8468 |
|
| 188 |
+
| No log | 2.6602 | 274 | 0.6875 | 0.5216 | 0.6875 | 0.8291 |
|
| 189 |
+
| No log | 2.6796 | 276 | 0.5170 | 0.5764 | 0.5170 | 0.7190 |
|
| 190 |
+
| No log | 2.6990 | 278 | 0.4238 | 0.6364 | 0.4238 | 0.6510 |
|
| 191 |
+
| No log | 2.7184 | 280 | 0.4218 | 0.6093 | 0.4218 | 0.6495 |
|
| 192 |
+
| No log | 2.7379 | 282 | 0.4345 | 0.6033 | 0.4345 | 0.6591 |
|
| 193 |
+
| No log | 2.7573 | 284 | 0.4275 | 0.6346 | 0.4275 | 0.6538 |
|
| 194 |
+
| No log | 2.7767 | 286 | 0.5344 | 0.6201 | 0.5344 | 0.7310 |
|
| 195 |
+
| No log | 2.7961 | 288 | 0.7891 | 0.4987 | 0.7891 | 0.8883 |
|
| 196 |
+
| No log | 2.8155 | 290 | 0.9135 | 0.4911 | 0.9135 | 0.9558 |
|
| 197 |
+
| No log | 2.8350 | 292 | 0.8427 | 0.5123 | 0.8427 | 0.9180 |
|
| 198 |
+
| No log | 2.8544 | 294 | 0.7493 | 0.5566 | 0.7493 | 0.8656 |
|
| 199 |
+
| No log | 2.8738 | 296 | 0.5960 | 0.6102 | 0.5960 | 0.7720 |
|
| 200 |
+
| No log | 2.8932 | 298 | 0.4786 | 0.6276 | 0.4786 | 0.6918 |
|
| 201 |
+
| No log | 2.9126 | 300 | 0.4459 | 0.6102 | 0.4459 | 0.6678 |
|
| 202 |
+
| No log | 2.9320 | 302 | 0.4336 | 0.6133 | 0.4336 | 0.6585 |
|
| 203 |
+
| No log | 2.9515 | 304 | 0.4466 | 0.6142 | 0.4466 | 0.6683 |
|
| 204 |
+
| No log | 2.9709 | 306 | 0.4584 | 0.6102 | 0.4584 | 0.6771 |
|
| 205 |
+
| No log | 2.9903 | 308 | 0.4251 | 0.5833 | 0.4251 | 0.6520 |
|
| 206 |
+
| No log | 3.0097 | 310 | 0.4224 | 0.6036 | 0.4224 | 0.6499 |
|
| 207 |
+
| No log | 3.0291 | 312 | 0.4492 | 0.6002 | 0.4492 | 0.6702 |
|
| 208 |
+
| No log | 3.0485 | 314 | 0.4830 | 0.6030 | 0.4830 | 0.6950 |
|
| 209 |
+
| No log | 3.0680 | 316 | 0.4908 | 0.6044 | 0.4908 | 0.7006 |
|
| 210 |
+
| No log | 3.0874 | 318 | 0.4911 | 0.6238 | 0.4911 | 0.7008 |
|
| 211 |
+
| No log | 3.1068 | 320 | 0.5672 | 0.5806 | 0.5672 | 0.7532 |
|
| 212 |
+
| No log | 3.1262 | 322 | 0.6404 | 0.5756 | 0.6404 | 0.8002 |
|
| 213 |
+
| No log | 3.1456 | 324 | 0.7038 | 0.5779 | 0.7038 | 0.8389 |
|
| 214 |
+
| No log | 3.1650 | 326 | 0.7906 | 0.5403 | 0.7906 | 0.8891 |
|
| 215 |
+
| No log | 3.1845 | 328 | 0.7678 | 0.5341 | 0.7678 | 0.8762 |
|
| 216 |
+
| No log | 3.2039 | 330 | 0.6490 | 0.5509 | 0.6490 | 0.8056 |
|
| 217 |
+
| No log | 3.2233 | 332 | 0.5750 | 0.5971 | 0.5750 | 0.7583 |
|
| 218 |
+
| No log | 3.2427 | 334 | 0.5504 | 0.6152 | 0.5504 | 0.7419 |
|
| 219 |
+
| No log | 3.2621 | 336 | 0.4612 | 0.6405 | 0.4612 | 0.6791 |
|
| 220 |
+
| No log | 3.2816 | 338 | 0.4261 | 0.6541 | 0.4261 | 0.6528 |
|
| 221 |
+
| No log | 3.3010 | 340 | 0.4072 | 0.6421 | 0.4072 | 0.6381 |
|
| 222 |
+
| No log | 3.3204 | 342 | 0.4145 | 0.6538 | 0.4145 | 0.6438 |
|
| 223 |
+
| No log | 3.3398 | 344 | 0.4319 | 0.6493 | 0.4319 | 0.6572 |
|
| 224 |
+
| No log | 3.3592 | 346 | 0.4687 | 0.6605 | 0.4687 | 0.6846 |
|
| 225 |
+
| No log | 3.3786 | 348 | 0.5407 | 0.6335 | 0.5407 | 0.7353 |
|
| 226 |
+
| No log | 3.3981 | 350 | 0.5732 | 0.6262 | 0.5732 | 0.7571 |
|
| 227 |
+
| No log | 3.4175 | 352 | 0.5355 | 0.6360 | 0.5355 | 0.7318 |
|
| 228 |
+
| No log | 3.4369 | 354 | 0.4905 | 0.6270 | 0.4905 | 0.7003 |
|
| 229 |
+
| No log | 3.4563 | 356 | 0.4299 | 0.6273 | 0.4299 | 0.6557 |
|
| 230 |
+
| No log | 3.4757 | 358 | 0.4029 | 0.6478 | 0.4029 | 0.6347 |
|
| 231 |
+
| No log | 3.4951 | 360 | 0.3946 | 0.6308 | 0.3946 | 0.6282 |
|
| 232 |
+
| No log | 3.5146 | 362 | 0.4185 | 0.6273 | 0.4185 | 0.6470 |
|
| 233 |
+
| No log | 3.5340 | 364 | 0.5554 | 0.6073 | 0.5554 | 0.7452 |
|
| 234 |
+
| No log | 3.5534 | 366 | 0.6614 | 0.5404 | 0.6614 | 0.8132 |
|
| 235 |
+
| No log | 3.5728 | 368 | 0.7019 | 0.5104 | 0.7019 | 0.8378 |
|
| 236 |
+
| No log | 3.5922 | 370 | 0.6041 | 0.5705 | 0.6041 | 0.7772 |
|
| 237 |
+
| No log | 3.6117 | 372 | 0.5413 | 0.5698 | 0.5413 | 0.7357 |
|
| 238 |
+
| No log | 3.6311 | 374 | 0.4869 | 0.5939 | 0.4869 | 0.6978 |
|
| 239 |
+
| No log | 3.6505 | 376 | 0.4548 | 0.6296 | 0.4548 | 0.6744 |
|
| 240 |
+
| No log | 3.6699 | 378 | 0.4633 | 0.6095 | 0.4633 | 0.6806 |
|
| 241 |
+
| No log | 3.6893 | 380 | 0.4621 | 0.5953 | 0.4621 | 0.6798 |
|
| 242 |
+
| No log | 3.7087 | 382 | 0.4718 | 0.6041 | 0.4718 | 0.6869 |
|
| 243 |
+
| No log | 3.7282 | 384 | 0.4684 | 0.6258 | 0.4684 | 0.6844 |
|
| 244 |
+
| No log | 3.7476 | 386 | 0.4581 | 0.6410 | 0.4581 | 0.6768 |
|
| 245 |
+
| No log | 3.7670 | 388 | 0.4472 | 0.6339 | 0.4472 | 0.6687 |
|
| 246 |
+
| No log | 3.7864 | 390 | 0.4586 | 0.6326 | 0.4586 | 0.6772 |
|
| 247 |
+
| No log | 3.8058 | 392 | 0.4880 | 0.6321 | 0.4880 | 0.6986 |
|
| 248 |
+
| No log | 3.8252 | 394 | 0.4700 | 0.6557 | 0.4700 | 0.6855 |
|
| 249 |
+
| No log | 3.8447 | 396 | 0.4541 | 0.6569 | 0.4541 | 0.6739 |
|
| 250 |
+
| No log | 3.8641 | 398 | 0.4796 | 0.6659 | 0.4796 | 0.6925 |
|
| 251 |
+
| No log | 3.8835 | 400 | 0.5397 | 0.6186 | 0.5397 | 0.7346 |
|
| 252 |
+
| No log | 3.9029 | 402 | 0.4911 | 0.6533 | 0.4911 | 0.7008 |
|
| 253 |
+
| No log | 3.9223 | 404 | 0.4801 | 0.6466 | 0.4801 | 0.6929 |
|
| 254 |
+
| No log | 3.9417 | 406 | 0.5555 | 0.5995 | 0.5555 | 0.7453 |
|
| 255 |
+
| No log | 3.9612 | 408 | 0.5316 | 0.5934 | 0.5316 | 0.7291 |
|
| 256 |
+
| No log | 3.9806 | 410 | 0.5020 | 0.5995 | 0.5020 | 0.7085 |
|
| 257 |
+
| No log | 4.0 | 412 | 0.4981 | 0.5969 | 0.4981 | 0.7057 |
|
| 258 |
+
| No log | 4.0194 | 414 | 0.4316 | 0.6385 | 0.4316 | 0.6570 |
|
| 259 |
+
| No log | 4.0388 | 416 | 0.4221 | 0.6486 | 0.4221 | 0.6497 |
|
| 260 |
+
| No log | 4.0583 | 418 | 0.5384 | 0.6021 | 0.5384 | 0.7338 |
|
| 261 |
+
| No log | 4.0777 | 420 | 0.6350 | 0.5818 | 0.6350 | 0.7969 |
|
| 262 |
+
| No log | 4.0971 | 422 | 0.6800 | 0.5814 | 0.6800 | 0.8246 |
|
| 263 |
+
| No log | 4.1165 | 424 | 0.7057 | 0.5761 | 0.7057 | 0.8401 |
|
| 264 |
+
| No log | 4.1359 | 426 | 0.7379 | 0.5711 | 0.7379 | 0.8590 |
|
| 265 |
+
| No log | 4.1553 | 428 | 0.6705 | 0.5737 | 0.6705 | 0.8188 |
|
| 266 |
+
| No log | 4.1748 | 430 | 0.5810 | 0.6039 | 0.5810 | 0.7623 |
|
| 267 |
+
| No log | 4.1942 | 432 | 0.5483 | 0.6398 | 0.5483 | 0.7405 |
|
| 268 |
+
| No log | 4.2136 | 434 | 0.5003 | 0.6394 | 0.5003 | 0.7073 |
|
| 269 |
+
| No log | 4.2330 | 436 | 0.4539 | 0.6544 | 0.4539 | 0.6737 |
|
| 270 |
+
| No log | 4.2524 | 438 | 0.4324 | 0.6472 | 0.4324 | 0.6576 |
|
| 271 |
+
| No log | 4.2718 | 440 | 0.4300 | 0.6375 | 0.4300 | 0.6558 |
|
| 272 |
+
| No log | 4.2913 | 442 | 0.5203 | 0.6289 | 0.5203 | 0.7213 |
|
| 273 |
+
| No log | 4.3107 | 444 | 0.5867 | 0.5736 | 0.5867 | 0.7659 |
|
| 274 |
+
| No log | 4.3301 | 446 | 0.5247 | 0.6038 | 0.5247 | 0.7243 |
|
| 275 |
+
| No log | 4.3495 | 448 | 0.4488 | 0.6146 | 0.4488 | 0.6699 |
|
| 276 |
+
| No log | 4.3689 | 450 | 0.4713 | 0.6336 | 0.4713 | 0.6865 |
|
| 277 |
+
| No log | 4.3883 | 452 | 0.5811 | 0.5884 | 0.5811 | 0.7623 |
|
| 278 |
+
| No log | 4.4078 | 454 | 0.6236 | 0.5594 | 0.6236 | 0.7897 |
|
| 279 |
+
| No log | 4.4272 | 456 | 0.5681 | 0.5724 | 0.5681 | 0.7537 |
|
| 280 |
+
| No log | 4.4466 | 458 | 0.5857 | 0.5725 | 0.5857 | 0.7653 |
|
| 281 |
+
| No log | 4.4660 | 460 | 0.5846 | 0.5711 | 0.5846 | 0.7646 |
|
| 282 |
+
| No log | 4.4854 | 462 | 0.5656 | 0.5873 | 0.5656 | 0.7520 |
|
| 283 |
+
| No log | 4.5049 | 464 | 0.5449 | 0.6024 | 0.5449 | 0.7382 |
|
| 284 |
+
| No log | 4.5243 | 466 | 0.5202 | 0.6282 | 0.5202 | 0.7212 |
|
| 285 |
+
| No log | 4.5437 | 468 | 0.5246 | 0.6144 | 0.5246 | 0.7243 |
|
| 286 |
+
| No log | 4.5631 | 470 | 0.5577 | 0.6117 | 0.5577 | 0.7468 |
|
| 287 |
+
| No log | 4.5825 | 472 | 0.6286 | 0.5410 | 0.6286 | 0.7929 |
|
| 288 |
+
| No log | 4.6019 | 474 | 0.8051 | 0.5247 | 0.8051 | 0.8973 |
|
| 289 |
+
| No log | 4.6214 | 476 | 0.9125 | 0.5233 | 0.9125 | 0.9552 |
|
| 290 |
+
| No log | 4.6408 | 478 | 0.9334 | 0.5226 | 0.9334 | 0.9661 |
|
| 291 |
+
| No log | 4.6602 | 480 | 0.8102 | 0.5450 | 0.8102 | 0.9001 |
|
| 292 |
+
| No log | 4.6796 | 482 | 0.6513 | 0.5556 | 0.6513 | 0.8071 |
|
| 293 |
+
| No log | 4.6990 | 484 | 0.5660 | 0.5882 | 0.5660 | 0.7523 |
|
| 294 |
+
| No log | 4.7184 | 486 | 0.5276 | 0.6018 | 0.5276 | 0.7264 |
|
| 295 |
+
| No log | 4.7379 | 488 | 0.4697 | 0.6267 | 0.4697 | 0.6854 |
|
| 296 |
+
| No log | 4.7573 | 490 | 0.4624 | 0.6242 | 0.4624 | 0.6800 |
|
| 297 |
+
| No log | 4.7767 | 492 | 0.5861 | 0.5688 | 0.5861 | 0.7656 |
|
| 298 |
+
| No log | 4.7961 | 494 | 0.6420 | 0.5097 | 0.6420 | 0.8013 |
|
| 299 |
+
| No log | 4.8155 | 496 | 0.5788 | 0.5086 | 0.5788 | 0.7608 |
|
| 300 |
+
| No log | 4.8350 | 498 | 0.4781 | 0.5888 | 0.4781 | 0.6914 |
|
| 301 |
+
| 0.4956 | 4.8544 | 500 | 0.4220 | 0.5638 | 0.4220 | 0.6496 |
|
| 302 |
+
| 0.4956 | 4.8738 | 502 | 0.4527 | 0.5877 | 0.4527 | 0.6728 |
|
| 303 |
+
| 0.4956 | 4.8932 | 504 | 0.4717 | 0.5949 | 0.4717 | 0.6868 |
|
| 304 |
+
| 0.4956 | 4.9126 | 506 | 0.4611 | 0.6301 | 0.4611 | 0.6791 |
|
| 305 |
+
| 0.4956 | 4.9320 | 508 | 0.4397 | 0.6200 | 0.4397 | 0.6631 |
|
| 306 |
+
| 0.4956 | 4.9515 | 510 | 0.4575 | 0.6355 | 0.4575 | 0.6764 |
|
| 307 |
+
| 0.4956 | 4.9709 | 512 | 0.5761 | 0.5819 | 0.5761 | 0.7590 |
|
| 308 |
+
| 0.4956 | 4.9903 | 514 | 0.7003 | 0.5429 | 0.7003 | 0.8368 |
|
| 309 |
+
| 0.4956 | 5.0097 | 516 | 0.6904 | 0.5373 | 0.6904 | 0.8309 |
|
| 310 |
+
| 0.4956 | 5.0291 | 518 | 0.5647 | 0.6143 | 0.5647 | 0.7515 |
|
| 311 |
+
| 0.4956 | 5.0485 | 520 | 0.4513 | 0.6601 | 0.4513 | 0.6718 |
|
| 312 |
+
| 0.4956 | 5.0680 | 522 | 0.4444 | 0.6498 | 0.4444 | 0.6667 |
|
| 313 |
+
| 0.4956 | 5.0874 | 524 | 0.4692 | 0.6278 | 0.4692 | 0.6850 |
|
| 314 |
+
| 0.4956 | 5.1068 | 526 | 0.5230 | 0.5899 | 0.5230 | 0.7232 |
|
| 315 |
+
| 0.4956 | 5.1262 | 528 | 0.5912 | 0.5897 | 0.5912 | 0.7689 |
|
| 316 |
+
| 0.4956 | 5.1456 | 530 | 0.6511 | 0.5854 | 0.6511 | 0.8069 |
|
| 317 |
+
| 0.4956 | 5.1650 | 532 | 0.6523 | 0.5820 | 0.6523 | 0.8077 |
|
| 318 |
+
| 0.4956 | 5.1845 | 534 | 0.5787 | 0.5640 | 0.5787 | 0.7607 |
|
| 319 |
+
| 0.4956 | 5.2039 | 536 | 0.5608 | 0.5573 | 0.5608 | 0.7489 |
|
| 320 |
+
| 0.4956 | 5.2233 | 538 | 0.4903 | 0.5851 | 0.4903 | 0.7002 |
|
| 321 |
+
| 0.4956 | 5.2427 | 540 | 0.4170 | 0.6208 | 0.4170 | 0.6457 |
|
| 322 |
+
| 0.4956 | 5.2621 | 542 | 0.4089 | 0.6126 | 0.4089 | 0.6394 |
|
| 323 |
+
| 0.4956 | 5.2816 | 544 | 0.4227 | 0.6020 | 0.4227 | 0.6502 |
|
| 324 |
+
| 0.4956 | 5.3010 | 546 | 0.5576 | 0.6126 | 0.5576 | 0.7467 |
|
| 325 |
+
| 0.4956 | 5.3204 | 548 | 0.8743 | 0.5081 | 0.8743 | 0.9350 |
|
| 326 |
+
| 0.4956 | 5.3398 | 550 | 0.9584 | 0.4835 | 0.9584 | 0.9790 |
|
| 327 |
+
| 0.4956 | 5.3592 | 552 | 0.8999 | 0.4997 | 0.8999 | 0.9486 |
|
| 328 |
+
| 0.4956 | 5.3786 | 554 | 0.7060 | 0.5792 | 0.7060 | 0.8403 |
|
| 329 |
+
| 0.4956 | 5.3981 | 556 | 0.4923 | 0.6452 | 0.4923 | 0.7016 |
|
| 330 |
+
| 0.4956 | 5.4175 | 558 | 0.4577 | 0.5770 | 0.4577 | 0.6766 |
|
| 331 |
+
| 0.4956 | 5.4369 | 560 | 0.4559 | 0.5746 | 0.4559 | 0.6752 |
|
| 332 |
+
| 0.4956 | 5.4563 | 562 | 0.4368 | 0.5998 | 0.4368 | 0.6609 |
|
| 333 |
+
| 0.4956 | 5.4757 | 564 | 0.4896 | 0.6751 | 0.4896 | 0.6997 |
|
| 334 |
+
| 0.4956 | 5.4951 | 566 | 0.6343 | 0.5811 | 0.6343 | 0.7964 |
|
| 335 |
+
| 0.4956 | 5.5146 | 568 | 0.6718 | 0.5644 | 0.6718 | 0.8196 |
|
| 336 |
+
| 0.4956 | 5.5340 | 570 | 0.6156 | 0.5824 | 0.6156 | 0.7846 |
|
| 337 |
+
| 0.4956 | 5.5534 | 572 | 0.6108 | 0.5585 | 0.6108 | 0.7815 |
|
| 338 |
+
| 0.4956 | 5.5728 | 574 | 0.6152 | 0.5454 | 0.6152 | 0.7844 |
|
| 339 |
+
| 0.4956 | 5.5922 | 576 | 0.6055 | 0.5629 | 0.6055 | 0.7781 |
|
| 340 |
+
| 0.4956 | 5.6117 | 578 | 0.5930 | 0.5590 | 0.5930 | 0.7701 |
|
| 341 |
+
| 0.4956 | 5.6311 | 580 | 0.5275 | 0.5680 | 0.5275 | 0.7263 |
|
| 342 |
+
| 0.4956 | 5.6505 | 582 | 0.4887 | 0.6062 | 0.4887 | 0.6991 |
|
| 343 |
+
| 0.4956 | 5.6699 | 584 | 0.4998 | 0.6036 | 0.4998 | 0.7070 |
|
| 344 |
+
| 0.4956 | 5.6893 | 586 | 0.5067 | 0.5900 | 0.5067 | 0.7118 |
|
| 345 |
+
| 0.4956 | 5.7087 | 588 | 0.5367 | 0.5928 | 0.5367 | 0.7326 |
|
| 346 |
+
| 0.4956 | 5.7282 | 590 | 0.5509 | 0.5878 | 0.5509 | 0.7422 |
|
| 347 |
+
| 0.4956 | 5.7476 | 592 | 0.5162 | 0.6061 | 0.5162 | 0.7185 |
|
| 348 |
+
| 0.4956 | 5.7670 | 594 | 0.4842 | 0.5798 | 0.4842 | 0.6959 |
|
| 349 |
+
| 0.4956 | 5.7864 | 596 | 0.4689 | 0.5510 | 0.4689 | 0.6848 |
|
| 350 |
+
| 0.4956 | 5.8058 | 598 | 0.4786 | 0.5557 | 0.4786 | 0.6918 |
|
| 351 |
+
| 0.4956 | 5.8252 | 600 | 0.5018 | 0.5562 | 0.5018 | 0.7084 |
|
| 352 |
+
| 0.4956 | 5.8447 | 602 | 0.5346 | 0.5680 | 0.5346 | 0.7311 |
|
| 353 |
+
| 0.4956 | 5.8641 | 604 | 0.6303 | 0.5488 | 0.6303 | 0.7939 |
|
| 354 |
+
| 0.4956 | 5.8835 | 606 | 0.7735 | 0.5383 | 0.7735 | 0.8795 |
|
| 355 |
+
| 0.4956 | 5.9029 | 608 | 0.7841 | 0.5567 | 0.7841 | 0.8855 |
|
| 356 |
+
| 0.4956 | 5.9223 | 610 | 0.7246 | 0.5504 | 0.7246 | 0.8512 |
|
| 357 |
+
| 0.4956 | 5.9417 | 612 | 0.6625 | 0.5624 | 0.6625 | 0.8139 |
|
| 358 |
+
|
| 359 |
+
|
| 360 |
+
### Framework versions
|
| 361 |
+
|
| 362 |
+
- Transformers 4.44.2
|
| 363 |
+
- Pytorch 2.4.0+cu118
|
| 364 |
+
- Datasets 2.21.0
|
| 365 |
+
- 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 sha256:172f347e75838075913289919f880d79e46b6d1f5cd0c06902a9bc8e45567281
|
| 3 |
+
size 540799996
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89609966e68afa4cfb07b4818020af43800e89569bbff0f1a6e4047e0041ba40
|
| 3 |
+
size 5240
|