Downloads · 30 days
9
1% of all-time downloads
child_mlm_30_age_5_english10000
Haerim/child_mlm_30_age_5_english10000
child_mlm_30_age_5_english10000 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
15.8M
5.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors63.4 MB · 96%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 20, 2026
- SHA
- 5bc77c2d
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_5_english10000
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4811
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 |
|---|---|---|---|
| 7.7619 | 3.6298 | 2000 | 7.2796 |
| 5.978 | 7.2595 | 4000 | 6.1312 |
| 5.8004 | 10.8893 | 6000 | 5.9962 |
| 5.6964 | 14.5191 | 8000 | 5.8827 |
| 5.614 | 18.1488 | 10000 | 5.8050 |
| 5.5637 | 21.7786 | 12000 | 5.7638 |
| 5.5308 | 25.4083 | 14000 | 5.7106 |
| 5.5039 | 29.0381 | 16000 | 5.7125 |
| 5.4823 | 32.6679 | 18000 | 5.7010 |
| 5.4701 | 36.2976 | 20000 | 5.6741 |
| 5.4609 | 39.9274 | 22000 | 5.6651 |
| 5.4507 | 43.5572 | 24000 | 5.6332 |
| 5.443 | 47.1869 | 26000 | 5.6395 |
| 5.4354 | 50.8167 | 28000 | 5.6149 |
| 5.4315 | 54.4465 | 30000 | 5.6199 |
| 5.4219 | 58.0762 | 32000 | 5.6015 |
| 5.4111 | 61.7060 | 34000 | 5.6032 |
| 5.4068 | 65.3358 | 36000 | 5.6040 |
| 5.4043 | 68.9655 | 38000 | 5.5719 |
| 5.3902 | 72.5953 | 40000 | 5.5747 |
| 4.9123 | 76.2250 | 42000 | 4.4815 |
| 3.7211 | 79.8548 | 44000 | 3.7233 |
| 3.2905 | 83.4846 | 46000 | 3.4151 |
| 3.0827 | 87.1143 | 48000 | 3.2533 |
| 2.9457 | 90.7441 | 50000 | 3.1501 |
| 2.8417 | 94.3739 | 52000 | 3.0513 |
| 2.7637 | 98.0036 | 54000 | 2.9659 |
| 2.7001 | 101.6334 | 56000 | 2.9233 |
| 2.6401 | 105.2632 | 58000 | 2.8561 |
| 2.5861 | 108.8929 | 60000 | 2.8197 |
| 2.5425 | 112.5227 | 62000 | 2.7809 |
| 2.505 | 116.1525 | 64000 | 2.7517 |
| 2.4769 | 119.7822 | 66000 | 2.6990 |
| 2.4464 | 123.4120 | 68000 | 2.6982 |
| 2.4165 | 127.0417 | 70000 | 2.6570 |
| 2.3921 | 130.6715 | 72000 | 2.6379 |
| 2.3673 | 134.3013 | 74000 | 2.6205 |
| 2.3442 | 137.9310 | 76000 | 2.6053 |
| 2.3284 | 141.5608 | 78000 | 2.5820 |
| 2.3107 | 145.1906 | 80000 | 2.5741 |
| 2.2976 | 148.8203 | 82000 | 2.5525 |
| 2.2821 | 152.4501 | 84000 | 2.5498 |
| 2.2706 | 156.0799 | 86000 | 2.5275 |
| 2.2589 | 159.7096 | 88000 | 2.5269 |
| 2.2516 | 163.3394 | 90000 | 2.5001 |
| 2.2399 | 166.9691 | 92000 | 2.5069 |
| 2.2361 | 170.5989 | 94000 | 2.5000 |
| 2.2284 | 174.2287 | 96000 | 2.5007 |
| 2.2254 | 177.8584 | 98000 | 2.5026 |
| 2.2227 | 181.4882 | 100000 | 2.4811 |
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