MercuraTech/reranker-de-all-classifier_1
Browse files- README.md +184 -0
- config.json +25 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: distilbert-base-german-cased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: classifier-de1
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# classifier-de1
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.3485
|
| 25 |
+
- Accuracy: 0.8738
|
| 26 |
+
- Precision: 0.4859
|
| 27 |
+
- Recall: 0.3069
|
| 28 |
+
- F1: 0.3762
|
| 29 |
+
|
| 30 |
+
## Model description
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training and evaluation data
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Training procedure
|
| 43 |
+
|
| 44 |
+
### Training hyperparameters
|
| 45 |
+
|
| 46 |
+
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 1.5e-05
|
| 48 |
+
- train_batch_size: 256
|
| 49 |
+
- eval_batch_size: 256
|
| 50 |
+
- seed: 42
|
| 51 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 6
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 59 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 60 |
+
| 0.3406 | 0.0513 | 500 | 0.3753 | 0.8760 | 0.0 | 0.0 | 0.0 |
|
| 61 |
+
| 0.3251 | 0.1025 | 1000 | 0.3678 | 0.8760 | 0.0 | 0.0 | 0.0 |
|
| 62 |
+
| 0.2989 | 0.1538 | 1500 | 0.3666 | 0.8756 | 0.2806 | 0.0021 | 0.0042 |
|
| 63 |
+
| 0.2989 | 0.2050 | 2000 | 0.3648 | 0.8734 | 0.4034 | 0.0430 | 0.0776 |
|
| 64 |
+
| 0.2922 | 0.2563 | 2500 | 0.3626 | 0.8746 | 0.4528 | 0.0545 | 0.0973 |
|
| 65 |
+
| 0.2757 | 0.3075 | 3000 | 0.3647 | 0.8690 | 0.3960 | 0.1072 | 0.1687 |
|
| 66 |
+
| 0.29 | 0.3588 | 3500 | 0.3584 | 0.8706 | 0.4192 | 0.1139 | 0.1791 |
|
| 67 |
+
| 0.2587 | 0.4100 | 4000 | 0.3690 | 0.8707 | 0.4287 | 0.1275 | 0.1965 |
|
| 68 |
+
| 0.2654 | 0.4613 | 4500 | 0.3626 | 0.8705 | 0.4310 | 0.1387 | 0.2098 |
|
| 69 |
+
| 0.2658 | 0.5125 | 5000 | 0.3585 | 0.8758 | 0.4958 | 0.1114 | 0.1820 |
|
| 70 |
+
| 0.2523 | 0.5638 | 5500 | 0.3527 | 0.8725 | 0.4556 | 0.1445 | 0.2194 |
|
| 71 |
+
| 0.2621 | 0.6150 | 6000 | 0.3522 | 0.8750 | 0.4855 | 0.1308 | 0.2061 |
|
| 72 |
+
| 0.2501 | 0.6663 | 6500 | 0.3556 | 0.8594 | 0.3934 | 0.2469 | 0.3034 |
|
| 73 |
+
| 0.2318 | 0.7175 | 7000 | 0.3536 | 0.8771 | 0.5181 | 0.1297 | 0.2075 |
|
| 74 |
+
| 0.2362 | 0.7688 | 7500 | 0.3424 | 0.8776 | 0.5279 | 0.1201 | 0.1956 |
|
| 75 |
+
| 0.2351 | 0.8200 | 8000 | 0.3354 | 0.8731 | 0.4723 | 0.2014 | 0.2823 |
|
| 76 |
+
| 0.2153 | 0.8713 | 8500 | 0.3426 | 0.8775 | 0.5198 | 0.1573 | 0.2416 |
|
| 77 |
+
| 0.215 | 0.9225 | 9000 | 0.3384 | 0.8785 | 0.5416 | 0.1323 | 0.2127 |
|
| 78 |
+
| 0.2177 | 0.9738 | 9500 | 0.3353 | 0.8749 | 0.4891 | 0.2040 | 0.2879 |
|
| 79 |
+
| 0.2173 | 1.0250 | 10000 | 0.3303 | 0.8729 | 0.4737 | 0.2243 | 0.3044 |
|
| 80 |
+
| 0.2128 | 1.0763 | 10500 | 0.3363 | 0.8770 | 0.5125 | 0.1677 | 0.2527 |
|
| 81 |
+
| 0.2093 | 1.1275 | 11000 | 0.3354 | 0.8720 | 0.4693 | 0.2471 | 0.3238 |
|
| 82 |
+
| 0.2022 | 1.1788 | 11500 | 0.3349 | 0.8752 | 0.4929 | 0.2122 | 0.2967 |
|
| 83 |
+
| 0.1978 | 1.2300 | 12000 | 0.3382 | 0.8722 | 0.4700 | 0.2421 | 0.3196 |
|
| 84 |
+
| 0.1974 | 1.2813 | 12500 | 0.3265 | 0.8753 | 0.4930 | 0.1923 | 0.2767 |
|
| 85 |
+
| 0.2185 | 1.3325 | 13000 | 0.3458 | 0.8755 | 0.4951 | 0.2055 | 0.2904 |
|
| 86 |
+
| 0.1973 | 1.3838 | 13500 | 0.3472 | 0.8738 | 0.4824 | 0.2482 | 0.3278 |
|
| 87 |
+
| 0.1946 | 1.4350 | 14000 | 0.3367 | 0.8779 | 0.5203 | 0.1915 | 0.2799 |
|
| 88 |
+
| 0.1986 | 1.4863 | 14500 | 0.3394 | 0.8717 | 0.4704 | 0.2750 | 0.3471 |
|
| 89 |
+
| 0.1922 | 1.5375 | 15000 | 0.3310 | 0.8770 | 0.5090 | 0.2321 | 0.3188 |
|
| 90 |
+
| 0.1765 | 1.5888 | 15500 | 0.3584 | 0.8797 | 0.5454 | 0.1779 | 0.2682 |
|
| 91 |
+
| 0.2039 | 1.6400 | 16000 | 0.3279 | 0.8774 | 0.5128 | 0.2290 | 0.3166 |
|
| 92 |
+
| 0.2051 | 1.6913 | 16500 | 0.3302 | 0.8794 | 0.5376 | 0.1970 | 0.2883 |
|
| 93 |
+
| 0.1868 | 1.7425 | 17000 | 0.3222 | 0.8763 | 0.5021 | 0.2498 | 0.3336 |
|
| 94 |
+
| 0.1972 | 1.7938 | 17500 | 0.3296 | 0.8685 | 0.4564 | 0.3163 | 0.3737 |
|
| 95 |
+
| 0.1932 | 1.8450 | 18000 | 0.3185 | 0.8776 | 0.5136 | 0.2399 | 0.3270 |
|
| 96 |
+
| 0.1797 | 1.8963 | 18500 | 0.3231 | 0.8768 | 0.5064 | 0.2446 | 0.3298 |
|
| 97 |
+
| 0.1835 | 1.9475 | 19000 | 0.3230 | 0.8748 | 0.4913 | 0.2729 | 0.3509 |
|
| 98 |
+
| 0.1767 | 1.9988 | 19500 | 0.3286 | 0.8756 | 0.4970 | 0.2566 | 0.3385 |
|
| 99 |
+
| 0.192 | 2.0500 | 20000 | 0.3304 | 0.8781 | 0.5183 | 0.2405 | 0.3285 |
|
| 100 |
+
| 0.1795 | 2.1013 | 20500 | 0.3333 | 0.8793 | 0.5326 | 0.2145 | 0.3059 |
|
| 101 |
+
| 0.1716 | 2.1525 | 21000 | 0.3499 | 0.8760 | 0.4998 | 0.2685 | 0.3493 |
|
| 102 |
+
| 0.177 | 2.2038 | 21500 | 0.3329 | 0.8775 | 0.5127 | 0.2395 | 0.3265 |
|
| 103 |
+
| 0.1541 | 2.2550 | 22000 | 0.3323 | 0.8781 | 0.5182 | 0.2444 | 0.3321 |
|
| 104 |
+
| 0.1725 | 2.3063 | 22500 | 0.3384 | 0.8799 | 0.5423 | 0.2033 | 0.2958 |
|
| 105 |
+
| 0.182 | 2.3575 | 23000 | 0.3326 | 0.8777 | 0.5138 | 0.2551 | 0.3409 |
|
| 106 |
+
| 0.1575 | 2.4088 | 23500 | 0.3373 | 0.8781 | 0.5188 | 0.2381 | 0.3264 |
|
| 107 |
+
| 0.1735 | 2.4600 | 24000 | 0.3436 | 0.8795 | 0.5331 | 0.2280 | 0.3194 |
|
| 108 |
+
| 0.1545 | 2.5113 | 24500 | 0.3400 | 0.8804 | 0.5447 | 0.2180 | 0.3114 |
|
| 109 |
+
| 0.1592 | 2.5625 | 25000 | 0.3422 | 0.8790 | 0.5272 | 0.2348 | 0.3249 |
|
| 110 |
+
| 0.1395 | 2.6138 | 25500 | 0.3583 | 0.8796 | 0.5358 | 0.2177 | 0.3096 |
|
| 111 |
+
| 0.1543 | 2.6650 | 26000 | 0.3341 | 0.8791 | 0.5296 | 0.2257 | 0.3165 |
|
| 112 |
+
| 0.1811 | 2.7163 | 26500 | 0.3245 | 0.8764 | 0.5032 | 0.2790 | 0.3589 |
|
| 113 |
+
| 0.1564 | 2.7675 | 27000 | 0.3395 | 0.8789 | 0.5246 | 0.2485 | 0.3373 |
|
| 114 |
+
| 0.1585 | 2.8188 | 27500 | 0.3465 | 0.8787 | 0.5221 | 0.2571 | 0.3445 |
|
| 115 |
+
| 0.1642 | 2.8700 | 28000 | 0.3545 | 0.8811 | 0.5508 | 0.2230 | 0.3174 |
|
| 116 |
+
| 0.1633 | 2.9213 | 28500 | 0.3339 | 0.8755 | 0.4963 | 0.2942 | 0.3694 |
|
| 117 |
+
| 0.1663 | 2.9725 | 29000 | 0.3398 | 0.8781 | 0.5166 | 0.2682 | 0.3531 |
|
| 118 |
+
| 0.136 | 3.0238 | 29500 | 0.3607 | 0.8807 | 0.5466 | 0.2240 | 0.3178 |
|
| 119 |
+
| 0.1409 | 3.0750 | 30000 | 0.3660 | 0.8793 | 0.5304 | 0.2336 | 0.3244 |
|
| 120 |
+
| 0.1474 | 3.1263 | 30500 | 0.3519 | 0.8763 | 0.5026 | 0.2635 | 0.3457 |
|
| 121 |
+
| 0.1505 | 3.1775 | 31000 | 0.3485 | 0.8738 | 0.4859 | 0.3069 | 0.3762 |
|
| 122 |
+
| 0.133 | 3.2288 | 31500 | 0.3578 | 0.8797 | 0.5357 | 0.2263 | 0.3182 |
|
| 123 |
+
| 0.1438 | 3.2800 | 32000 | 0.3455 | 0.8758 | 0.4985 | 0.2839 | 0.3617 |
|
| 124 |
+
| 0.1591 | 3.3313 | 32500 | 0.3373 | 0.8749 | 0.4929 | 0.3033 | 0.3755 |
|
| 125 |
+
| 0.1738 | 3.3825 | 33000 | 0.3446 | 0.8781 | 0.5169 | 0.2656 | 0.3509 |
|
| 126 |
+
| 0.1683 | 3.4338 | 33500 | 0.3380 | 0.8776 | 0.5123 | 0.2721 | 0.3554 |
|
| 127 |
+
| 0.1567 | 3.4850 | 34000 | 0.3493 | 0.8799 | 0.5338 | 0.2481 | 0.3387 |
|
| 128 |
+
| 0.1388 | 3.5363 | 34500 | 0.3463 | 0.8791 | 0.5255 | 0.2557 | 0.3440 |
|
| 129 |
+
| 0.15 | 3.5875 | 35000 | 0.3391 | 0.8811 | 0.5454 | 0.2465 | 0.3396 |
|
| 130 |
+
| 0.1478 | 3.6388 | 35500 | 0.3465 | 0.8799 | 0.5327 | 0.2544 | 0.3444 |
|
| 131 |
+
| 0.1359 | 3.6900 | 36000 | 0.3705 | 0.8798 | 0.5321 | 0.2515 | 0.3416 |
|
| 132 |
+
| 0.1502 | 3.7413 | 36500 | 0.3386 | 0.8790 | 0.5236 | 0.2653 | 0.3522 |
|
| 133 |
+
| 0.1387 | 3.7925 | 37000 | 0.3514 | 0.8789 | 0.5227 | 0.2719 | 0.3577 |
|
| 134 |
+
| 0.1484 | 3.8438 | 37500 | 0.3391 | 0.8805 | 0.5432 | 0.2283 | 0.3215 |
|
| 135 |
+
| 0.154 | 3.8950 | 38000 | 0.3584 | 0.8807 | 0.5456 | 0.2259 | 0.3195 |
|
| 136 |
+
| 0.1395 | 3.9463 | 38500 | 0.3403 | 0.8779 | 0.5137 | 0.2804 | 0.3628 |
|
| 137 |
+
| 0.1429 | 3.9975 | 39000 | 0.3467 | 0.8783 | 0.5172 | 0.2747 | 0.3588 |
|
| 138 |
+
| 0.1278 | 4.0488 | 39500 | 0.3581 | 0.8793 | 0.5272 | 0.2609 | 0.3491 |
|
| 139 |
+
| 0.1582 | 4.1000 | 40000 | 0.3483 | 0.8783 | 0.5179 | 0.2719 | 0.3566 |
|
| 140 |
+
| 0.1174 | 4.1513 | 40500 | 0.3587 | 0.8794 | 0.5279 | 0.2604 | 0.3487 |
|
| 141 |
+
| 0.1363 | 4.2025 | 41000 | 0.3594 | 0.8800 | 0.5347 | 0.2514 | 0.3420 |
|
| 142 |
+
| 0.1361 | 4.2538 | 41500 | 0.3664 | 0.8806 | 0.5414 | 0.2426 | 0.3350 |
|
| 143 |
+
| 0.1299 | 4.3050 | 42000 | 0.3603 | 0.8792 | 0.5258 | 0.2606 | 0.3485 |
|
| 144 |
+
| 0.1443 | 4.3563 | 42500 | 0.3705 | 0.8796 | 0.5296 | 0.2616 | 0.3502 |
|
| 145 |
+
| 0.1417 | 4.4075 | 43000 | 0.3611 | 0.8800 | 0.5350 | 0.2455 | 0.3366 |
|
| 146 |
+
| 0.1354 | 4.4588 | 43500 | 0.3523 | 0.8792 | 0.5249 | 0.2735 | 0.3596 |
|
| 147 |
+
| 0.1474 | 4.5100 | 44000 | 0.3683 | 0.8812 | 0.5481 | 0.2384 | 0.3323 |
|
| 148 |
+
| 0.1398 | 4.5613 | 44500 | 0.3537 | 0.8800 | 0.5328 | 0.2599 | 0.3494 |
|
| 149 |
+
| 0.1558 | 4.6125 | 45000 | 0.3529 | 0.8804 | 0.5391 | 0.2466 | 0.3384 |
|
| 150 |
+
| 0.1479 | 4.6638 | 45500 | 0.3489 | 0.8794 | 0.5270 | 0.2640 | 0.3518 |
|
| 151 |
+
| 0.1454 | 4.7150 | 46000 | 0.3618 | 0.8798 | 0.5309 | 0.2620 | 0.3508 |
|
| 152 |
+
| 0.1327 | 4.7663 | 46500 | 0.3634 | 0.8807 | 0.5423 | 0.2444 | 0.3369 |
|
| 153 |
+
| 0.1427 | 4.8175 | 47000 | 0.3578 | 0.8784 | 0.5175 | 0.2836 | 0.3664 |
|
| 154 |
+
| 0.1361 | 4.8688 | 47500 | 0.3531 | 0.8794 | 0.5272 | 0.2693 | 0.3565 |
|
| 155 |
+
| 0.1303 | 4.9200 | 48000 | 0.3636 | 0.8789 | 0.5231 | 0.2627 | 0.3498 |
|
| 156 |
+
| 0.1373 | 4.9713 | 48500 | 0.3528 | 0.8791 | 0.5252 | 0.2628 | 0.3503 |
|
| 157 |
+
| 0.1339 | 5.0226 | 49000 | 0.3662 | 0.8795 | 0.5286 | 0.2631 | 0.3513 |
|
| 158 |
+
| 0.1449 | 5.0738 | 49500 | 0.3603 | 0.8773 | 0.5095 | 0.2778 | 0.3596 |
|
| 159 |
+
| 0.1295 | 5.1251 | 50000 | 0.3811 | 0.8795 | 0.5284 | 0.2616 | 0.3499 |
|
| 160 |
+
| 0.1372 | 5.1763 | 50500 | 0.3637 | 0.8769 | 0.5065 | 0.2885 | 0.3676 |
|
| 161 |
+
| 0.1381 | 5.2276 | 51000 | 0.3629 | 0.8784 | 0.5176 | 0.2833 | 0.3662 |
|
| 162 |
+
| 0.1334 | 5.2788 | 51500 | 0.3639 | 0.8788 | 0.5219 | 0.2672 | 0.3535 |
|
| 163 |
+
| 0.1422 | 5.3301 | 52000 | 0.3694 | 0.8779 | 0.5147 | 0.2729 | 0.3566 |
|
| 164 |
+
| 0.1413 | 5.3813 | 52500 | 0.3610 | 0.8773 | 0.5097 | 0.2822 | 0.3633 |
|
| 165 |
+
| 0.1487 | 5.4326 | 53000 | 0.3650 | 0.8778 | 0.5136 | 0.2736 | 0.3570 |
|
| 166 |
+
| 0.1431 | 5.4838 | 53500 | 0.3704 | 0.8797 | 0.5309 | 0.2567 | 0.3461 |
|
| 167 |
+
| 0.142 | 5.5351 | 54000 | 0.3637 | 0.8794 | 0.5278 | 0.2607 | 0.3490 |
|
| 168 |
+
| 0.1406 | 5.5863 | 54500 | 0.3670 | 0.8790 | 0.5243 | 0.2641 | 0.3512 |
|
| 169 |
+
| 0.1484 | 5.6376 | 55000 | 0.3608 | 0.8775 | 0.5109 | 0.2793 | 0.3612 |
|
| 170 |
+
| 0.1433 | 5.6888 | 55500 | 0.3652 | 0.8787 | 0.5211 | 0.2705 | 0.3562 |
|
| 171 |
+
| 0.1219 | 5.7401 | 56000 | 0.3655 | 0.8782 | 0.5165 | 0.2759 | 0.3597 |
|
| 172 |
+
| 0.1344 | 5.7913 | 56500 | 0.3662 | 0.8790 | 0.5242 | 0.2649 | 0.3519 |
|
| 173 |
+
| 0.1598 | 5.8426 | 57000 | 0.3684 | 0.8787 | 0.5208 | 0.2727 | 0.3580 |
|
| 174 |
+
| 0.1287 | 5.8938 | 57500 | 0.3659 | 0.8791 | 0.5240 | 0.2692 | 0.3556 |
|
| 175 |
+
| 0.1182 | 5.9451 | 58000 | 0.3671 | 0.8793 | 0.5263 | 0.2657 | 0.3531 |
|
| 176 |
+
| 0.1242 | 5.9963 | 58500 | 0.3650 | 0.8790 | 0.5234 | 0.2693 | 0.3556 |
|
| 177 |
+
|
| 178 |
+
|
| 179 |
+
### Framework versions
|
| 180 |
+
|
| 181 |
+
- Transformers 4.51.3
|
| 182 |
+
- Pytorch 2.7.0+cu126
|
| 183 |
+
- Datasets 3.5.0
|
| 184 |
+
- Tokenizers 0.21.1
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"output_past": true,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": true,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.51.3",
|
| 24 |
+
"vocab_size": 31102
|
| 25 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25185e88349a01ac797e1c1b397a9c37b1963f3da16404664a35fe9dc32850c1
|
| 3 |
+
size 269614320
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"101": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"102": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"103": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"104": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63980f5d984bf7904756283bb3be9e681256f4e8721a850f104784b13ad804c1
|
| 3 |
+
size 5649
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|