Downloads · 30 days
10
38% of all-time downloads
morphs_marks_lex_6_layers_8_att_heads_5_seqlen
martijn75/morphs_marks_lex_6_layers_8_att_heads_5_seqlen
morphs_marks_lex_6_layers_8_att_heads_5_seqlen is a fill-mask model from martijn75. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
26
Public
Parameters
7.1M
85.9 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin28.6 MB · 50%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Aug 13, 2025
- Updated
- Aug 13, 2025
- SHA
- 167dd671
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
morphs_marks_lex_6_layers_8_att_heads_5_seqlen
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9987
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.6142 | 1.0 | 1762 | 5.5071 |
| 5.3606 | 2.0 | 3524 | 5.3186 |
| 5.2631 | 3.0 | 5286 | 5.1807 |
| 5.1738 | 4.0 | 7048 | 5.1532 |
| 5.1092 | 5.0 | 8810 | 5.1478 |
| 5.0761 | 6.0 | 10572 | 5.0430 |
| 5.0622 | 7.0 | 12334 | 5.0108 |
| 5.0121 | 8.0 | 14096 | 5.0031 |
| 5.0011 | 9.0 | 15858 | 4.9458 |
| 4.9378 | 10.0 | 17620 | 4.9379 |
| 4.9524 | 11.0 | 19382 | 4.9557 |
| 4.8684 | 12.0 | 21144 | 4.9022 |
| 4.8681 | 13.0 | 22906 | 4.8984 |
| 4.8423 | 14.0 | 24668 | 4.8433 |
| 4.8215 | 15.0 | 26430 | 4.8776 |
| 4.833 | 16.0 | 28192 | 4.8479 |
| 4.7942 | 17.0 | 29954 | 4.8044 |
| 4.7861 | 18.0 | 31716 | 4.8222 |
| 4.7599 | 19.0 | 33478 | 4.7516 |
| 4.7095 | 20.0 | 35240 | 4.7283 |
| 4.6987 | 21.0 | 37002 | 4.7058 |
| 4.7004 | 22.0 | 38764 | 4.7535 |
| 4.6899 | 23.0 | 40526 | 4.6840 |
| 4.6849 | 24.0 | 42288 | 4.6641 |
| 4.6462 | 25.0 | 44050 | 4.6360 |
| 4.5919 | 26.0 | 45812 | 4.5552 |
| 4.5929 | 27.0 | 47574 | 4.5489 |
| 4.553 | 28.0 | 49336 | 4.4708 |
| 4.4947 | 29.0 | 51098 | 4.4235 |
| 4.4756 | 30.0 | 52860 | 4.3753 |
| 4.4395 | 31.0 | 54622 | 4.3377 |
| 4.4293 | 32.0 | 56384 | 4.3029 |
| 4.3878 | 33.0 | 58146 | 4.2345 |
| 4.3789 | 34.0 | 59908 | 4.1737 |
| 4.2634 | 35.0 | 61670 | 4.1269 |
| 4.238 | 36.0 | 63432 | 4.0676 |
| 4.1997 | 37.0 | 65194 | 3.9973 |
| 4.208 | 38.0 | 66956 | 3.9556 |
| 4.1422 | 39.0 | 68718 | 3.9087 |
| 4.0748 | 40.0 | 70480 | 3.7894 |
| 4.0602 | 41.0 | 72242 | 3.8099 |
| 4.0053 | 42.0 | 74004 | 3.7128 |
| 3.9691 | 43.0 | 75766 | 3.6800 |
| 3.9592 | 44.0 | 77528 | 3.6538 |
| 3.9088 | 45.0 | 79290 | 3.6403 |
| 3.8929 | 46.0 | 81052 | 3.5699 |
| 3.8308 | 47.0 | 82814 | 3.5354 |
| 3.7637 | 48.0 | 84576 | 3.5177 |
| 3.7892 | 49.0 | 86338 | 3.4779 |
| 3.7313 | 50.0 | 88100 | 3.4804 |
| 3.7026 | 51.0 | 89862 | 3.4401 |
| 3.6391 | 52.0 | 91624 | 3.4357 |
| 3.634 | 53.0 | 93386 | 3.3988 |
| 3.5949 | 54.0 | 95148 | 3.4056 |
| 3.6081 | 55.0 | 96910 | 3.3175 |
| 3.5871 | 56.0 | 98672 | 3.3605 |
| 3.5087 | 57.0 | 100434 | 3.3384 |
| 3.4891 | 58.0 | 102196 | 3.3243 |
| 3.5328 | 59.0 | 103958 | 3.2655 |
| 3.4787 | 60.0 | 105720 | 3.2460 |
| 3.4415 | 61.0 | 107482 | 3.2362 |
| 3.4439 | 62.0 | 109244 | 3.2184 |
| 3.405 | 63.0 | 111006 | 3.2378 |
| 3.4118 | 64.0 | 112768 | 3.2383 |
| 3.385 | 65.0 | 114530 | 3.2170 |
| 3.3352 | 66.0 | 116292 | 3.2069 |
| 3.3248 | 67.0 | 118054 | 3.1932 |
| 3.3247 | 68.0 | 119816 | 3.1626 |
| 3.3011 | 69.0 | 121578 | 3.1392 |
| 3.3155 | 70.0 | 123340 | 3.1383 |
| 3.2616 | 71.0 | 125102 | 3.1366 |
| 3.2755 | 72.0 | 126864 | 3.1243 |
| 3.2484 | 73.0 | 128626 | 3.0936 |
| 3.2184 | 74.0 | 130388 | 3.0805 |
| 3.2374 | 75.0 | 132150 | 3.1240 |
| 3.2768 | 76.0 | 133912 | 3.0678 |
| 3.1901 | 77.0 | 135674 | 3.0778 |
| 3.194 | 78.0 | 137436 | 3.1195 |
| 3.2545 | 79.0 | 139198 | 3.0635 |
| 3.195 | 80.0 | 140960 | 3.0783 |
| 3.1412 | 81.0 | 142722 | 3.0379 |
| 3.1593 | 82.0 | 144484 | 3.0515 |
| 3.1914 | 83.0 | 146246 | 3.0266 |
| 3.1585 | 84.0 | 148008 | 3.0207 |
| 3.1643 | 85.0 | 149770 | 3.0493 |
| 3.1474 | 86.0 | 151532 | 3.0405 |
| 3.1329 | 87.0 | 153294 | 3.0260 |
| 3.1167 | 88.0 | 155056 | 2.9774 |
| 3.1092 | 89.0 | 156818 | 3.0353 |
| 3.1498 | 90.0 | 158580 | 2.9994 |
| 3.1068 | 91.0 | 160342 | 3.0195 |
| 3.1057 | 92.0 | 162104 | 2.9987 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Aug 13, 2025
- Updated
- Aug 13, 2025