Downloads · 30 days
28
2% of all-time downloads
child_mlm_30_age_3_english900
Haerim/child_mlm_30_age_3_english900
child_mlm_30_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
1.5K
Public
Parameters
11.2M
7.5 GB on disk
Likes
1
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 20, 2026
- SHA
- 0b38d73f
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_3_english900
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0586
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: 1000
- training_steps: 100000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.849 | 4.3243 | 2000 | 4.8835 |
| 4.8032 | 8.6486 | 4000 | 4.8546 |
| 4.7951 | 12.9730 | 6000 | 4.8455 |
| 4.7891 | 17.2973 | 8000 | 4.8379 |
| 4.7886 | 21.6216 | 10000 | 4.8394 |
| 4.7861 | 25.9459 | 12000 | 4.8187 |
| 4.7742 | 30.2703 | 14000 | 4.8145 |
| 4.7568 | 34.5946 | 16000 | 4.7789 |
| 3.6614 | 38.9189 | 18000 | 3.1535 |
| 2.7087 | 43.2432 | 20000 | 2.4721 |
| 2.2881 | 47.5676 | 22000 | 2.1541 |
| 2.0705 | 51.8919 | 24000 | 1.9749 |
| 1.9217 | 56.2162 | 26000 | 1.8493 |
| 1.8106 | 60.5405 | 28000 | 1.7499 |
| 1.7301 | 64.8649 | 30000 | 1.6866 |
| 1.6656 | 69.1892 | 32000 | 1.6402 |
| 1.6057 | 73.5135 | 34000 | 1.5741 |
| 1.5533 | 77.8378 | 36000 | 1.5292 |
| 1.5042 | 82.1622 | 38000 | 1.4786 |
| 1.4505 | 86.4865 | 40000 | 1.4204 |
| 1.4035 | 90.8108 | 42000 | 1.3794 |
| 1.3666 | 95.1351 | 44000 | 1.3514 |
| 1.3292 | 99.4595 | 46000 | 1.3165 |
| 1.2993 | 103.7838 | 48000 | 1.2916 |
| 1.2725 | 108.1081 | 50000 | 1.2631 |
| 1.2499 | 112.4324 | 52000 | 1.2488 |
| 1.2299 | 116.7568 | 54000 | 1.2213 |
| 1.212 | 121.0811 | 56000 | 1.2167 |
| 1.1957 | 125.4054 | 58000 | 1.1994 |
| 1.1796 | 129.7297 | 60000 | 1.1799 |
| 1.1618 | 134.0541 | 62000 | 1.1664 |
| 1.1468 | 138.3784 | 64000 | 1.1478 |
| 1.1331 | 142.7027 | 66000 | 1.1406 |
| 1.1231 | 147.0270 | 68000 | 1.1246 |
| 1.1135 | 151.3514 | 70000 | 1.1144 |
| 1.1034 | 155.6757 | 72000 | 1.1087 |
| 1.0975 | 160.0 | 74000 | 1.1162 |
| 1.0862 | 164.3243 | 76000 | 1.1051 |
| 1.0801 | 168.6486 | 78000 | 1.0974 |
| 1.072 | 172.9730 | 80000 | 1.0942 |
| 1.0659 | 177.2973 | 82000 | 1.0824 |
| 1.0581 | 181.6216 | 84000 | 1.0730 |
| 1.0583 | 185.9459 | 86000 | 1.0695 |
| 1.0536 | 190.2703 | 88000 | 1.0628 |
| 1.0491 | 194.5946 | 90000 | 1.0610 |
| 1.041 | 198.9189 | 92000 | 1.0552 |
| 1.0386 | 203.2432 | 94000 | 1.0580 |
| 1.0375 | 207.5676 | 96000 | 1.0693 |
| 1.0344 | 211.8919 | 98000 | 1.0581 |
| 1.0328 | 216.2162 | 100000 | 1.0586 |
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