Downloads · 30 days
2
0% of all-time downloads
child_mlm_13_age_3_english900
Haerim/child_mlm_13_age_3_english900
child_mlm_13_age_3_english900 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
1.2K
Public
Parameters
11.2M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors44.7 MB · 97%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 18, 2026
- SHA
- d866fb77
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_13_age_3_english900
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0570
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: 13
- 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: 1000
- training_steps: 100000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8485 | 4.3243 | 2000 | 4.8859 |
| 4.8043 | 8.6486 | 4000 | 4.8438 |
| 4.7949 | 12.9730 | 6000 | 4.8263 |
| 4.7872 | 17.2973 | 8000 | 4.8147 |
| 4.784 | 21.6216 | 10000 | 4.8265 |
| 4.7791 | 25.9459 | 12000 | 4.8289 |
| 4.7766 | 30.2703 | 14000 | 4.8207 |
| 4.7652 | 34.5946 | 16000 | 4.8019 |
| 4.594 | 38.9189 | 18000 | 4.1648 |
| 3.1853 | 43.2432 | 20000 | 2.8679 |
| 2.5888 | 47.5676 | 22000 | 2.4362 |
| 2.3253 | 51.8919 | 24000 | 2.2283 |
| 2.1719 | 56.2162 | 26000 | 2.1011 |
| 2.0618 | 60.5405 | 28000 | 1.9999 |
| 1.9796 | 64.8649 | 30000 | 1.9396 |
| 1.9116 | 69.1892 | 32000 | 1.8739 |
| 1.8563 | 73.5135 | 34000 | 1.8352 |
| 1.7924 | 77.8378 | 36000 | 1.7443 |
| 1.7131 | 82.1622 | 38000 | 1.6749 |
| 1.6124 | 86.4865 | 40000 | 1.5551 |
| 1.5059 | 90.8108 | 42000 | 1.4443 |
| 1.438 | 95.1351 | 44000 | 1.4003 |
| 1.39 | 99.4595 | 46000 | 1.3556 |
| 1.3509 | 103.7838 | 48000 | 1.3195 |
| 1.3165 | 108.1081 | 50000 | 1.3101 |
| 1.282 | 112.4324 | 52000 | 1.2680 |
| 1.257 | 116.7568 | 54000 | 1.2390 |
| 1.2331 | 121.0811 | 56000 | 1.2206 |
| 1.2096 | 125.4054 | 58000 | 1.2076 |
| 1.1916 | 129.7297 | 60000 | 1.1985 |
| 1.1738 | 134.0541 | 62000 | 1.1741 |
| 1.1621 | 138.3784 | 64000 | 1.1596 |
| 1.1488 | 142.7027 | 66000 | 1.1433 |
| 1.1365 | 147.0270 | 68000 | 1.1435 |
| 1.1241 | 151.3514 | 70000 | 1.1451 |
| 1.1159 | 155.6757 | 72000 | 1.1247 |
| 1.1065 | 160.0 | 74000 | 1.1204 |
| 1.0996 | 164.3243 | 76000 | 1.1141 |
| 1.0912 | 168.6486 | 78000 | 1.1023 |
| 1.0832 | 172.9730 | 80000 | 1.1118 |
| 1.0749 | 177.2973 | 82000 | 1.1008 |
| 1.0723 | 181.6216 | 84000 | 1.0851 |
| 1.0625 | 185.9459 | 86000 | 1.0742 |
| 1.057 | 190.2703 | 88000 | 1.0797 |
| 1.0514 | 194.5946 | 90000 | 1.0564 |
| 1.0487 | 198.9189 | 92000 | 1.0652 |
| 1.0436 | 203.2432 | 94000 | 1.0681 |
| 1.0429 | 207.5676 | 96000 | 1.0593 |
| 1.0397 | 211.8919 | 98000 | 1.0651 |
| 1.0386 | 216.2162 | 100000 | 1.0570 |
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 18, 2026