kugler/bert-base-german-cased-amdi-synset
Browse files- README.md +194 -0
- config.json +158 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
model-index:
|
| 11 |
+
- name: bert-base-german-cased-amdi-synset
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# bert-base-german-cased-amdi-synset
|
| 19 |
+
|
| 20 |
+
This model was trained from scratch on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.7086
|
| 23 |
+
- Accuracy: 0.8055
|
| 24 |
+
- F1: 0.5536
|
| 25 |
+
- Precision: 0.5654
|
| 26 |
+
- Recall: 0.5744
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 5e-05
|
| 46 |
+
- train_batch_size: 8
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 10
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 57 |
+
| 3.7615 | 0.0765 | 50 | 3.1888 | 0.2874 | 0.0867 | 0.0882 | 0.1287 |
|
| 58 |
+
| 2.6256 | 0.1529 | 100 | 1.9358 | 0.6299 | 0.2547 | 0.2377 | 0.3115 |
|
| 59 |
+
| 1.5993 | 0.2294 | 150 | 1.4048 | 0.6678 | 0.2951 | 0.2620 | 0.3522 |
|
| 60 |
+
| 1.4846 | 0.3058 | 200 | 1.2470 | 0.6644 | 0.3032 | 0.2756 | 0.3724 |
|
| 61 |
+
| 1.1822 | 0.3823 | 250 | 1.1040 | 0.7143 | 0.3859 | 0.4011 | 0.4329 |
|
| 62 |
+
| 1.1861 | 0.4587 | 300 | 0.9793 | 0.7315 | 0.4110 | 0.4163 | 0.4500 |
|
| 63 |
+
| 0.9813 | 0.5352 | 350 | 0.9844 | 0.7177 | 0.3638 | 0.3368 | 0.4152 |
|
| 64 |
+
| 1.0233 | 0.6116 | 400 | 0.8853 | 0.7315 | 0.3922 | 0.3827 | 0.4400 |
|
| 65 |
+
| 0.9335 | 0.6881 | 450 | 0.8682 | 0.7229 | 0.4029 | 0.3761 | 0.4555 |
|
| 66 |
+
| 0.8632 | 0.7645 | 500 | 0.8938 | 0.7074 | 0.3958 | 0.3929 | 0.4395 |
|
| 67 |
+
| 0.8554 | 0.8410 | 550 | 0.8641 | 0.7349 | 0.4354 | 0.4495 | 0.4842 |
|
| 68 |
+
| 0.745 | 0.9174 | 600 | 0.7404 | 0.7694 | 0.4471 | 0.4487 | 0.4852 |
|
| 69 |
+
| 0.8285 | 0.9939 | 650 | 0.7802 | 0.7556 | 0.4373 | 0.4304 | 0.4871 |
|
| 70 |
+
| 0.6485 | 1.0703 | 700 | 0.7980 | 0.7522 | 0.4645 | 0.5001 | 0.5074 |
|
| 71 |
+
| 0.7505 | 1.1468 | 750 | 0.7127 | 0.7556 | 0.4711 | 0.4691 | 0.5112 |
|
| 72 |
+
| 0.5805 | 1.2232 | 800 | 0.7690 | 0.7762 | 0.4965 | 0.5064 | 0.5126 |
|
| 73 |
+
| 0.6321 | 1.2997 | 850 | 0.7761 | 0.7625 | 0.4863 | 0.4991 | 0.5119 |
|
| 74 |
+
| 0.6786 | 1.3761 | 900 | 0.7174 | 0.7952 | 0.4955 | 0.5092 | 0.5159 |
|
| 75 |
+
| 0.6474 | 1.4526 | 950 | 0.7714 | 0.7762 | 0.4972 | 0.4989 | 0.5204 |
|
| 76 |
+
| 0.6404 | 1.5291 | 1000 | 0.7914 | 0.7539 | 0.4575 | 0.4634 | 0.4901 |
|
| 77 |
+
| 0.593 | 1.6055 | 1050 | 0.7073 | 0.7780 | 0.5103 | 0.5142 | 0.5448 |
|
| 78 |
+
| 0.5835 | 1.6820 | 1100 | 0.7399 | 0.7866 | 0.5209 | 0.5177 | 0.5573 |
|
| 79 |
+
| 0.6412 | 1.7584 | 1150 | 0.6477 | 0.8124 | 0.5439 | 0.5451 | 0.5699 |
|
| 80 |
+
| 0.4541 | 1.8349 | 1200 | 0.7352 | 0.7780 | 0.5149 | 0.5318 | 0.5468 |
|
| 81 |
+
| 0.7073 | 1.9113 | 1250 | 0.6252 | 0.8003 | 0.5313 | 0.5134 | 0.5742 |
|
| 82 |
+
| 0.5594 | 1.9878 | 1300 | 0.6769 | 0.7935 | 0.5535 | 0.5738 | 0.5820 |
|
| 83 |
+
| 0.5304 | 2.0642 | 1350 | 0.6631 | 0.8124 | 0.5716 | 0.5704 | 0.6021 |
|
| 84 |
+
| 0.3383 | 2.1407 | 1400 | 0.6642 | 0.8021 | 0.5527 | 0.5709 | 0.5776 |
|
| 85 |
+
| 0.3957 | 2.2171 | 1450 | 0.6631 | 0.8193 | 0.5803 | 0.5811 | 0.5950 |
|
| 86 |
+
| 0.3652 | 2.2936 | 1500 | 0.7086 | 0.8055 | 0.5536 | 0.5654 | 0.5744 |
|
| 87 |
+
| 0.4445 | 2.3700 | 1550 | 0.7142 | 0.8003 | 0.5558 | 0.5605 | 0.5908 |
|
| 88 |
+
| 0.411 | 2.4465 | 1600 | 0.7134 | 0.8072 | 0.5644 | 0.5798 | 0.5742 |
|
| 89 |
+
| 0.5233 | 2.5229 | 1650 | 0.6846 | 0.8107 | 0.5466 | 0.5523 | 0.5646 |
|
| 90 |
+
| 0.407 | 2.5994 | 1700 | 0.6663 | 0.8158 | 0.5586 | 0.5669 | 0.5740 |
|
| 91 |
+
| 0.378 | 2.6758 | 1750 | 0.7391 | 0.8124 | 0.5642 | 0.5787 | 0.5854 |
|
| 92 |
+
| 0.3595 | 2.7523 | 1800 | 0.7391 | 0.8176 | 0.5747 | 0.5935 | 0.5896 |
|
| 93 |
+
| 0.4271 | 2.8287 | 1850 | 0.7237 | 0.8176 | 0.5753 | 0.5796 | 0.5980 |
|
| 94 |
+
| 0.3514 | 2.9052 | 1900 | 0.7601 | 0.8244 | 0.5717 | 0.5853 | 0.5849 |
|
| 95 |
+
| 0.4118 | 2.9817 | 1950 | 0.6944 | 0.8176 | 0.5809 | 0.5895 | 0.5986 |
|
| 96 |
+
| 0.3361 | 3.0581 | 2000 | 0.7427 | 0.8176 | 0.5828 | 0.5853 | 0.6047 |
|
| 97 |
+
| 0.2835 | 3.1346 | 2050 | 0.7423 | 0.8210 | 0.5698 | 0.5776 | 0.5826 |
|
| 98 |
+
| 0.2791 | 3.2110 | 2100 | 0.8072 | 0.8090 | 0.5544 | 0.5630 | 0.5710 |
|
| 99 |
+
| 0.3093 | 3.2875 | 2150 | 0.8117 | 0.8158 | 0.5648 | 0.5690 | 0.5838 |
|
| 100 |
+
| 0.2683 | 3.3639 | 2200 | 0.7990 | 0.8296 | 0.5710 | 0.5679 | 0.5854 |
|
| 101 |
+
| 0.2549 | 3.4404 | 2250 | 0.8160 | 0.8348 | 0.5872 | 0.5914 | 0.6003 |
|
| 102 |
+
| 0.2647 | 3.5168 | 2300 | 0.8324 | 0.8330 | 0.5925 | 0.5943 | 0.6044 |
|
| 103 |
+
| 0.2367 | 3.5933 | 2350 | 0.8226 | 0.8227 | 0.5946 | 0.5961 | 0.6100 |
|
| 104 |
+
| 0.2644 | 3.6697 | 2400 | 0.9041 | 0.8193 | 0.5908 | 0.5995 | 0.6083 |
|
| 105 |
+
| 0.3544 | 3.7462 | 2450 | 0.9154 | 0.8141 | 0.5825 | 0.5962 | 0.6005 |
|
| 106 |
+
| 0.2654 | 3.8226 | 2500 | 0.8085 | 0.8210 | 0.6050 | 0.6159 | 0.6208 |
|
| 107 |
+
| 0.2305 | 3.8991 | 2550 | 0.8421 | 0.8262 | 0.5759 | 0.5798 | 0.5917 |
|
| 108 |
+
| 0.3305 | 3.9755 | 2600 | 0.8312 | 0.8193 | 0.6068 | 0.6288 | 0.6139 |
|
| 109 |
+
| 0.2711 | 4.0520 | 2650 | 0.8650 | 0.8210 | 0.5859 | 0.5939 | 0.5924 |
|
| 110 |
+
| 0.137 | 4.1284 | 2700 | 0.8813 | 0.8227 | 0.5809 | 0.5876 | 0.5966 |
|
| 111 |
+
| 0.2072 | 4.2049 | 2750 | 0.8558 | 0.8348 | 0.6091 | 0.6353 | 0.6184 |
|
| 112 |
+
| 0.226 | 4.2813 | 2800 | 0.8628 | 0.8296 | 0.5861 | 0.5835 | 0.6021 |
|
| 113 |
+
| 0.153 | 4.3578 | 2850 | 0.8712 | 0.8382 | 0.6062 | 0.6157 | 0.6110 |
|
| 114 |
+
| 0.125 | 4.4343 | 2900 | 0.8996 | 0.8417 | 0.6179 | 0.6234 | 0.6282 |
|
| 115 |
+
| 0.1186 | 4.5107 | 2950 | 0.8958 | 0.8382 | 0.6098 | 0.6103 | 0.6198 |
|
| 116 |
+
| 0.1498 | 4.5872 | 3000 | 0.9907 | 0.8072 | 0.5869 | 0.5980 | 0.6086 |
|
| 117 |
+
| 0.1228 | 4.6636 | 3050 | 0.9276 | 0.8244 | 0.6113 | 0.6243 | 0.6234 |
|
| 118 |
+
| 0.0896 | 4.7401 | 3100 | 0.8962 | 0.8348 | 0.6265 | 0.6358 | 0.6379 |
|
| 119 |
+
| 0.1722 | 4.8165 | 3150 | 0.9404 | 0.8244 | 0.5922 | 0.5897 | 0.6162 |
|
| 120 |
+
| 0.2493 | 4.8930 | 3200 | 0.9081 | 0.8279 | 0.6016 | 0.5913 | 0.6259 |
|
| 121 |
+
| 0.1868 | 4.9694 | 3250 | 0.9450 | 0.8330 | 0.6024 | 0.6044 | 0.6191 |
|
| 122 |
+
| 0.0714 | 5.0459 | 3300 | 0.9498 | 0.8279 | 0.6039 | 0.6125 | 0.6228 |
|
| 123 |
+
| 0.0967 | 5.1223 | 3350 | 0.9723 | 0.8244 | 0.6094 | 0.6166 | 0.6265 |
|
| 124 |
+
| 0.1341 | 5.1988 | 3400 | 0.9906 | 0.8227 | 0.5975 | 0.6125 | 0.6120 |
|
| 125 |
+
| 0.1067 | 5.2752 | 3450 | 0.9759 | 0.8313 | 0.5980 | 0.6042 | 0.6169 |
|
| 126 |
+
| 0.05 | 5.3517 | 3500 | 0.9823 | 0.8296 | 0.5967 | 0.6034 | 0.6133 |
|
| 127 |
+
| 0.0561 | 5.4281 | 3550 | 1.0020 | 0.8313 | 0.6041 | 0.6098 | 0.6224 |
|
| 128 |
+
| 0.0716 | 5.5046 | 3600 | 1.0264 | 0.8279 | 0.6013 | 0.6107 | 0.6113 |
|
| 129 |
+
| 0.0476 | 5.5810 | 3650 | 1.0426 | 0.8296 | 0.6125 | 0.6216 | 0.6277 |
|
| 130 |
+
| 0.135 | 5.6575 | 3700 | 1.0367 | 0.8227 | 0.6401 | 0.6618 | 0.6490 |
|
| 131 |
+
| 0.0948 | 5.7339 | 3750 | 0.9911 | 0.8399 | 0.6507 | 0.6599 | 0.6557 |
|
| 132 |
+
| 0.0306 | 5.8104 | 3800 | 0.9729 | 0.8382 | 0.6400 | 0.6468 | 0.6495 |
|
| 133 |
+
| 0.1203 | 5.8869 | 3850 | 1.0240 | 0.8244 | 0.6230 | 0.6453 | 0.6272 |
|
| 134 |
+
| 0.1401 | 5.9633 | 3900 | 1.0078 | 0.8279 | 0.6191 | 0.6400 | 0.6251 |
|
| 135 |
+
| 0.0875 | 6.0398 | 3950 | 1.0308 | 0.8279 | 0.6023 | 0.6201 | 0.6089 |
|
| 136 |
+
| 0.0568 | 6.1162 | 4000 | 0.9964 | 0.8262 | 0.5989 | 0.6137 | 0.6049 |
|
| 137 |
+
| 0.0364 | 6.1927 | 4050 | 0.9775 | 0.8313 | 0.6067 | 0.6301 | 0.6126 |
|
| 138 |
+
| 0.0391 | 6.2691 | 4100 | 1.0063 | 0.8313 | 0.6323 | 0.6539 | 0.6364 |
|
| 139 |
+
| 0.0327 | 6.3456 | 4150 | 1.0221 | 0.8227 | 0.6136 | 0.6231 | 0.6175 |
|
| 140 |
+
| 0.0587 | 6.4220 | 4200 | 1.0493 | 0.8262 | 0.6308 | 0.6408 | 0.6347 |
|
| 141 |
+
| 0.0421 | 6.4985 | 4250 | 1.0646 | 0.8296 | 0.6228 | 0.6367 | 0.6281 |
|
| 142 |
+
| 0.0397 | 6.5749 | 4300 | 1.0177 | 0.8262 | 0.6156 | 0.6359 | 0.6211 |
|
| 143 |
+
| 0.0425 | 6.6514 | 4350 | 1.0295 | 0.8296 | 0.6239 | 0.6360 | 0.6286 |
|
| 144 |
+
| 0.0206 | 6.7278 | 4400 | 1.0322 | 0.8348 | 0.6261 | 0.6485 | 0.6294 |
|
| 145 |
+
| 0.0438 | 6.8043 | 4450 | 1.0312 | 0.8296 | 0.6076 | 0.6173 | 0.6115 |
|
| 146 |
+
| 0.0515 | 6.8807 | 4500 | 1.0735 | 0.8193 | 0.6137 | 0.6150 | 0.6249 |
|
| 147 |
+
| 0.0768 | 6.9572 | 4550 | 1.1468 | 0.8193 | 0.6056 | 0.6143 | 0.6133 |
|
| 148 |
+
| 0.0427 | 7.0336 | 4600 | 1.0917 | 0.8193 | 0.6005 | 0.6127 | 0.6042 |
|
| 149 |
+
| 0.0254 | 7.1101 | 4650 | 1.1042 | 0.8210 | 0.6026 | 0.6165 | 0.6035 |
|
| 150 |
+
| 0.006 | 7.1865 | 4700 | 1.1204 | 0.8176 | 0.5793 | 0.5914 | 0.5826 |
|
| 151 |
+
| 0.0321 | 7.2630 | 4750 | 1.1171 | 0.8227 | 0.5957 | 0.6048 | 0.5993 |
|
| 152 |
+
| 0.0292 | 7.3394 | 4800 | 1.1265 | 0.8141 | 0.5930 | 0.6047 | 0.5946 |
|
| 153 |
+
| 0.0158 | 7.4159 | 4850 | 1.1176 | 0.8193 | 0.6040 | 0.6164 | 0.6046 |
|
| 154 |
+
| 0.0273 | 7.4924 | 4900 | 1.1194 | 0.8210 | 0.6052 | 0.6146 | 0.6094 |
|
| 155 |
+
| 0.0467 | 7.5688 | 4950 | 1.1171 | 0.8176 | 0.6121 | 0.6222 | 0.6158 |
|
| 156 |
+
| 0.0155 | 7.6453 | 5000 | 1.1207 | 0.8227 | 0.6067 | 0.6196 | 0.6085 |
|
| 157 |
+
| 0.0158 | 7.7217 | 5050 | 1.1188 | 0.8262 | 0.6216 | 0.6394 | 0.6212 |
|
| 158 |
+
| 0.0383 | 7.7982 | 5100 | 1.0977 | 0.8330 | 0.6242 | 0.6412 | 0.6250 |
|
| 159 |
+
| 0.0535 | 7.8746 | 5150 | 1.1085 | 0.8330 | 0.6249 | 0.6431 | 0.6262 |
|
| 160 |
+
| 0.0478 | 7.9511 | 5200 | 1.1164 | 0.8382 | 0.6470 | 0.6651 | 0.6481 |
|
| 161 |
+
| 0.0275 | 8.0275 | 5250 | 1.1208 | 0.8399 | 0.6598 | 0.6765 | 0.6630 |
|
| 162 |
+
| 0.0076 | 8.1040 | 5300 | 1.1152 | 0.8365 | 0.6416 | 0.6574 | 0.6416 |
|
| 163 |
+
| 0.0153 | 8.1804 | 5350 | 1.1129 | 0.8348 | 0.6395 | 0.6562 | 0.6390 |
|
| 164 |
+
| 0.0077 | 8.2569 | 5400 | 1.1243 | 0.8330 | 0.6431 | 0.6620 | 0.6417 |
|
| 165 |
+
| 0.0116 | 8.3333 | 5450 | 1.1258 | 0.8330 | 0.6393 | 0.6593 | 0.6382 |
|
| 166 |
+
| 0.0083 | 8.4098 | 5500 | 1.1212 | 0.8330 | 0.6302 | 0.6490 | 0.6307 |
|
| 167 |
+
| 0.0291 | 8.4862 | 5550 | 1.1340 | 0.8330 | 0.6405 | 0.6600 | 0.6411 |
|
| 168 |
+
| 0.0202 | 8.5627 | 5600 | 1.1388 | 0.8348 | 0.6423 | 0.6616 | 0.6426 |
|
| 169 |
+
| 0.0333 | 8.6391 | 5650 | 1.1452 | 0.8313 | 0.6299 | 0.6484 | 0.6300 |
|
| 170 |
+
| 0.0045 | 8.7156 | 5700 | 1.1460 | 0.8382 | 0.6552 | 0.6739 | 0.6544 |
|
| 171 |
+
| 0.0201 | 8.7920 | 5750 | 1.1466 | 0.8365 | 0.6495 | 0.6676 | 0.6492 |
|
| 172 |
+
| 0.0133 | 8.8685 | 5800 | 1.1461 | 0.8348 | 0.6474 | 0.6664 | 0.6465 |
|
| 173 |
+
| 0.0317 | 8.9450 | 5850 | 1.1530 | 0.8348 | 0.6430 | 0.6614 | 0.6435 |
|
| 174 |
+
| 0.0065 | 9.0214 | 5900 | 1.1490 | 0.8313 | 0.6400 | 0.6588 | 0.6404 |
|
| 175 |
+
| 0.0035 | 9.0979 | 5950 | 1.1545 | 0.8313 | 0.6443 | 0.6646 | 0.6435 |
|
| 176 |
+
| 0.0104 | 9.1743 | 6000 | 1.1619 | 0.8313 | 0.6459 | 0.6654 | 0.6454 |
|
| 177 |
+
| 0.0109 | 9.2508 | 6050 | 1.1603 | 0.8313 | 0.6459 | 0.6654 | 0.6454 |
|
| 178 |
+
| 0.0028 | 9.3272 | 6100 | 1.1563 | 0.8330 | 0.6474 | 0.6668 | 0.6471 |
|
| 179 |
+
| 0.0157 | 9.4037 | 6150 | 1.1553 | 0.8348 | 0.6480 | 0.6672 | 0.6478 |
|
| 180 |
+
| 0.0072 | 9.4801 | 6200 | 1.1530 | 0.8313 | 0.6417 | 0.6565 | 0.6433 |
|
| 181 |
+
| 0.0064 | 9.5566 | 6250 | 1.1572 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 182 |
+
| 0.0183 | 9.6330 | 6300 | 1.1586 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 183 |
+
| 0.0221 | 9.7095 | 6350 | 1.1592 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 184 |
+
| 0.0129 | 9.7859 | 6400 | 1.1599 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 185 |
+
| 0.014 | 9.8624 | 6450 | 1.1590 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 186 |
+
| 0.0019 | 9.9388 | 6500 | 1.1596 | 0.8296 | 0.6401 | 0.6552 | 0.6416 |
|
| 187 |
+
|
| 188 |
+
|
| 189 |
+
### Framework versions
|
| 190 |
+
|
| 191 |
+
- Transformers 4.45.2
|
| 192 |
+
- Pytorch 2.3.1+cu121
|
| 193 |
+
- Datasets 2.20.0
|
| 194 |
+
- Tokenizers 0.20.3
|
config.json
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/media/data/models/bert-base-german-cased",
|
| 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": "s24528",
|
| 13 |
+
"1": "s11270",
|
| 14 |
+
"10": "s14251",
|
| 15 |
+
"11": "s42158",
|
| 16 |
+
"12": "s29644",
|
| 17 |
+
"13": "sxxxxx",
|
| 18 |
+
"14": "s7419",
|
| 19 |
+
"15": "s6399",
|
| 20 |
+
"16": "s73683",
|
| 21 |
+
"17": "s13438",
|
| 22 |
+
"18": "s7282",
|
| 23 |
+
"19": "s41895",
|
| 24 |
+
"2": "s47771",
|
| 25 |
+
"20": "s50968",
|
| 26 |
+
"21": "s106689",
|
| 27 |
+
"22": "s33154",
|
| 28 |
+
"23": "s6029",
|
| 29 |
+
"24": "s25993",
|
| 30 |
+
"25": "s15791",
|
| 31 |
+
"26": "s47572",
|
| 32 |
+
"27": "s26149",
|
| 33 |
+
"28": "s10855",
|
| 34 |
+
"29": "s10206",
|
| 35 |
+
"3": "s10649",
|
| 36 |
+
"30": "s25245",
|
| 37 |
+
"31": "s30016",
|
| 38 |
+
"32": "s33676",
|
| 39 |
+
"33": "s50922",
|
| 40 |
+
"34": "s41951",
|
| 41 |
+
"35": "s7930",
|
| 42 |
+
"36": "s11625",
|
| 43 |
+
"37": "s110427",
|
| 44 |
+
"38": "s10313",
|
| 45 |
+
"39": "s64010",
|
| 46 |
+
"4": "s107180",
|
| 47 |
+
"40": "s42868",
|
| 48 |
+
"41": "s26446",
|
| 49 |
+
"42": "s9697",
|
| 50 |
+
"43": "s46736",
|
| 51 |
+
"44": "s73727",
|
| 52 |
+
"45": "s10919",
|
| 53 |
+
"46": "s9650",
|
| 54 |
+
"47": "s107850",
|
| 55 |
+
"48": "s33599",
|
| 56 |
+
"49": "s63143",
|
| 57 |
+
"5": "s9544",
|
| 58 |
+
"50": "s12102",
|
| 59 |
+
"51": "s75975",
|
| 60 |
+
"52": "s33132",
|
| 61 |
+
"53": "s107685",
|
| 62 |
+
"54": "s37889",
|
| 63 |
+
"55": "s25671",
|
| 64 |
+
"56": "s6390",
|
| 65 |
+
"57": "s33659",
|
| 66 |
+
"58": "s110889",
|
| 67 |
+
"59": "s69017",
|
| 68 |
+
"6": "s23151",
|
| 69 |
+
"60": "s106690",
|
| 70 |
+
"61": "s10937",
|
| 71 |
+
"62": "s106691",
|
| 72 |
+
"63": "s85055",
|
| 73 |
+
"7": "s11307",
|
| 74 |
+
"8": "s10304",
|
| 75 |
+
"9": "s9426"
|
| 76 |
+
},
|
| 77 |
+
"initializer_range": 0.02,
|
| 78 |
+
"intermediate_size": 3072,
|
| 79 |
+
"label2id": {
|
| 80 |
+
"s10206": 29,
|
| 81 |
+
"s10304": 8,
|
| 82 |
+
"s10313": 38,
|
| 83 |
+
"s10649": 3,
|
| 84 |
+
"s106689": 21,
|
| 85 |
+
"s106690": 60,
|
| 86 |
+
"s106691": 62,
|
| 87 |
+
"s107180": 4,
|
| 88 |
+
"s107685": 53,
|
| 89 |
+
"s107850": 47,
|
| 90 |
+
"s10855": 28,
|
| 91 |
+
"s10919": 45,
|
| 92 |
+
"s10937": 61,
|
| 93 |
+
"s110427": 37,
|
| 94 |
+
"s110889": 58,
|
| 95 |
+
"s11270": 1,
|
| 96 |
+
"s11307": 7,
|
| 97 |
+
"s11625": 36,
|
| 98 |
+
"s12102": 50,
|
| 99 |
+
"s13438": 17,
|
| 100 |
+
"s14251": 10,
|
| 101 |
+
"s15791": 25,
|
| 102 |
+
"s23151": 6,
|
| 103 |
+
"s24528": 0,
|
| 104 |
+
"s25245": 30,
|
| 105 |
+
"s25671": 55,
|
| 106 |
+
"s25993": 24,
|
| 107 |
+
"s26149": 27,
|
| 108 |
+
"s26446": 41,
|
| 109 |
+
"s29644": 12,
|
| 110 |
+
"s30016": 31,
|
| 111 |
+
"s33132": 52,
|
| 112 |
+
"s33154": 22,
|
| 113 |
+
"s33599": 48,
|
| 114 |
+
"s33659": 57,
|
| 115 |
+
"s33676": 32,
|
| 116 |
+
"s37889": 54,
|
| 117 |
+
"s41895": 19,
|
| 118 |
+
"s41951": 34,
|
| 119 |
+
"s42158": 11,
|
| 120 |
+
"s42868": 40,
|
| 121 |
+
"s46736": 43,
|
| 122 |
+
"s47572": 26,
|
| 123 |
+
"s47771": 2,
|
| 124 |
+
"s50922": 33,
|
| 125 |
+
"s50968": 20,
|
| 126 |
+
"s6029": 23,
|
| 127 |
+
"s63143": 49,
|
| 128 |
+
"s6390": 56,
|
| 129 |
+
"s6399": 15,
|
| 130 |
+
"s64010": 39,
|
| 131 |
+
"s69017": 59,
|
| 132 |
+
"s7282": 18,
|
| 133 |
+
"s73683": 16,
|
| 134 |
+
"s73727": 44,
|
| 135 |
+
"s7419": 14,
|
| 136 |
+
"s75975": 51,
|
| 137 |
+
"s7930": 35,
|
| 138 |
+
"s85055": 63,
|
| 139 |
+
"s9426": 9,
|
| 140 |
+
"s9544": 5,
|
| 141 |
+
"s9650": 46,
|
| 142 |
+
"s9697": 42,
|
| 143 |
+
"sxxxxx": 13
|
| 144 |
+
},
|
| 145 |
+
"layer_norm_eps": 1e-12,
|
| 146 |
+
"max_position_embeddings": 512,
|
| 147 |
+
"model_type": "bert",
|
| 148 |
+
"num_attention_heads": 12,
|
| 149 |
+
"num_hidden_layers": 12,
|
| 150 |
+
"pad_token_id": 0,
|
| 151 |
+
"position_embedding_type": "absolute",
|
| 152 |
+
"problem_type": "single_label_classification",
|
| 153 |
+
"torch_dtype": "float32",
|
| 154 |
+
"transformers_version": "4.45.2",
|
| 155 |
+
"type_vocab_size": 2,
|
| 156 |
+
"use_cache": true,
|
| 157 |
+
"vocab_size": 30000
|
| 158 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a66978d00817dc7af03c868e95d4b3c517fb35cb04c2a27a51f443cbd0e04279
|
| 3 |
+
size 436545768
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:109e97be28a0c2b35fb928a49ee21748d1a161187ed677f8ce03eefbe5e25226
|
| 3 |
+
size 5240
|