Downloads · 30 days
2
0% of all-time downloads
child_mlm_30_age_7_english20000
Haerim/child_mlm_30_age_7_english20000
child_mlm_30_age_7_english20000 is a fill-mask model from Haerim. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1.1K
Public
Parameters
21M
11.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors83.9 MB · 96%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 20, 2026
- SHA
- 3db2431e
Try a prompt
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. -->
child_mlm_30_age_7_english20000
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5157
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: 16
- eval_batch_size: 16
- seed: 30
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.2916 | 3.3585 | 2000 | 7.7332 |
| 6.0307 | 6.7170 | 4000 | 6.1233 |
| 5.8087 | 10.0756 | 6000 | 6.0001 |
| 5.6979 | 13.4341 | 8000 | 5.9006 |
| 5.6192 | 16.7926 | 10000 | 5.8065 |
| 5.5608 | 20.1511 | 12000 | 5.7498 |
| 5.5239 | 23.5097 | 14000 | 5.7112 |
| 5.4968 | 26.8682 | 16000 | 5.7074 |
| 5.4793 | 30.2267 | 18000 | 5.6778 |
| 5.4617 | 33.5852 | 20000 | 5.6646 |
| 5.4536 | 36.9437 | 22000 | 5.6398 |
| 5.4376 | 40.3023 | 24000 | 5.6341 |
| 5.4336 | 43.6608 | 26000 | 5.6258 |
| 5.4322 | 47.0193 | 28000 | 5.6026 |
| 5.4158 | 50.3778 | 30000 | 5.6328 |
| 5.4104 | 53.7364 | 32000 | 5.6061 |
| 5.4019 | 57.0949 | 34000 | 5.5981 |
| 5.3988 | 60.4534 | 36000 | 5.5886 |
| 5.3841 | 63.8119 | 38000 | 5.5616 |
| 5.3222 | 67.1704 | 40000 | 5.3880 |
| 3.8309 | 70.5290 | 42000 | 3.8089 |
| 3.2451 | 73.8875 | 44000 | 3.4069 |
| 3.0048 | 77.2460 | 46000 | 3.2105 |
| 2.8674 | 80.6045 | 48000 | 3.0783 |
| 2.7661 | 83.9631 | 50000 | 3.0130 |
| 2.6906 | 87.3216 | 52000 | 2.9507 |
| 2.6178 | 90.6801 | 54000 | 2.8698 |
| 2.5682 | 94.0386 | 56000 | 2.8429 |
| 2.5158 | 97.3971 | 58000 | 2.7807 |
| 2.478 | 100.7557 | 60000 | 2.7618 |
| 2.4393 | 104.1142 | 62000 | 2.7108 |
| 2.4079 | 107.4727 | 64000 | 2.6930 |
| 2.3758 | 110.8312 | 66000 | 2.6760 |
| 2.3506 | 114.1898 | 68000 | 2.6417 |
| 2.326 | 117.5483 | 70000 | 2.6314 |
| 2.3081 | 120.9068 | 72000 | 2.6063 |
| 2.29 | 124.2653 | 74000 | 2.5987 |
| 2.274 | 127.6238 | 76000 | 2.5854 |
| 2.2578 | 130.9824 | 78000 | 2.5885 |
| 2.2449 | 134.3409 | 80000 | 2.5701 |
| 2.2348 | 137.6994 | 82000 | 2.5480 |
| 2.2202 | 141.0579 | 84000 | 2.5483 |
| 2.2096 | 144.4165 | 86000 | 2.5352 |
| 2.2028 | 147.7750 | 88000 | 2.5311 |
| 2.1966 | 151.1335 | 90000 | 2.5193 |
| 2.1895 | 154.4920 | 92000 | 2.5138 |
| 2.1788 | 157.8505 | 94000 | 2.5149 |
| 2.1757 | 161.2091 | 96000 | 2.5045 |
| 2.1715 | 164.5676 | 98000 | 2.5120 |
| 2.1732 | 167.9261 | 100000 | 2.5157 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.11.0+cu128
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- May 2, 2026
- Updated
- May 20, 2026