Downloads · 30 days
3
0% of all-time downloads
child_mlm_13_age_4_english2000
Haerim/child_mlm_13_age_4_english2000
child_mlm_13_age_4_english2000 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
1K
Public
Parameters
11.7M
3.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47 MB · 97%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 18, 2026
- SHA
- e90a8984
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_4_english2000
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5959
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: 40000
- training_steps: 100000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.4084 | 4.0363 | 2000 | 6.1538 |
| 5.6351 | 8.0727 | 4000 | 5.6968 |
| 5.4629 | 12.1090 | 6000 | 5.5436 |
| 5.3505 | 16.1453 | 8000 | 5.4433 |
| 5.2827 | 20.1816 | 10000 | 5.3974 |
| 5.2449 | 24.2180 | 12000 | 5.3564 |
| 5.227 | 28.2543 | 14000 | 5.3477 |
| 5.218 | 32.2906 | 16000 | 5.3254 |
| 5.2102 | 36.3269 | 18000 | 5.3114 |
| 5.2082 | 40.3633 | 20000 | 5.3182 |
| 5.2015 | 44.3996 | 22000 | 5.2978 |
| 5.1987 | 48.4359 | 24000 | 5.2980 |
| 5.1991 | 52.4723 | 26000 | 5.3074 |
| 5.1953 | 56.5086 | 28000 | 5.2739 |
| 5.1948 | 60.5449 | 30000 | 5.2872 |
| 5.1914 | 64.5812 | 32000 | 5.2842 |
| 5.1914 | 68.6176 | 34000 | 5.2940 |
| 5.1897 | 72.6539 | 36000 | 5.2861 |
| 5.1899 | 76.6902 | 38000 | 5.2732 |
| 5.1778 | 80.7265 | 40000 | 5.2700 |
| 5.1768 | 84.7629 | 42000 | 5.2804 |
| 5.1643 | 88.7992 | 44000 | 5.2595 |
| 5.1142 | 92.8355 | 46000 | 5.1268 |
| 3.8141 | 96.8718 | 48000 | 3.4927 |
| 2.9814 | 100.9082 | 50000 | 2.8203 |
| 2.5914 | 104.9445 | 52000 | 2.5331 |
| 2.3651 | 108.9808 | 54000 | 2.3541 |
| 2.2159 | 113.0172 | 56000 | 2.2090 |
| 2.0957 | 117.0535 | 58000 | 2.1266 |
| 2.0144 | 121.0898 | 60000 | 2.0317 |
| 1.9497 | 125.1261 | 62000 | 1.9969 |
| 1.8944 | 129.1625 | 64000 | 1.9328 |
| 1.851 | 133.1988 | 66000 | 1.9052 |
| 1.8041 | 137.2351 | 68000 | 1.8472 |
| 1.7589 | 141.2714 | 70000 | 1.7931 |
| 1.7233 | 145.3078 | 72000 | 1.7630 |
| 1.6786 | 149.3441 | 74000 | 1.7209 |
| 1.6522 | 153.3804 | 76000 | 1.6976 |
| 1.6297 | 157.4168 | 78000 | 1.6770 |
| 1.6085 | 161.4531 | 80000 | 1.6605 |
| 1.5864 | 165.4894 | 82000 | 1.6535 |
| 1.5711 | 169.5257 | 84000 | 1.6219 |
| 1.5551 | 173.5621 | 86000 | 1.6109 |
| 1.5466 | 177.5984 | 88000 | 1.5972 |
| 1.5365 | 181.6347 | 90000 | 1.5914 |
| 1.5244 | 185.6710 | 92000 | 1.5900 |
| 1.5201 | 189.7074 | 94000 | 1.6033 |
| 1.5135 | 193.7437 | 96000 | 1.5760 |
| 1.5083 | 197.7800 | 98000 | 1.5761 |
| 1.5059 | 201.8163 | 100000 | 1.5959 |
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