Downloads · 30 days
6
1% of all-time downloads
QBert
wenda2025/QBert
QBert is a fill-mask model from wenda2025. 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
68M
80.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors544 MB · 50%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- qbert
- Access
- Public
- Created
- Apr 24, 2026
- Updated
- May 7, 2026
- SHA
- 75f93462
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. -->
QBert
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4291
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 603
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7876 | 4.0161 | 2000 | 5.7572 |
| 5.6570 | 8.0321 | 4000 | 5.6031 |
| 5.4869 | 12.0482 | 6000 | 5.0994 |
| 4.7571 | 16.0643 | 8000 | 4.4091 |
| 4.2246 | 20.0803 | 10000 | 3.9246 |
| 3.6582 | 24.0964 | 12000 | 3.1099 |
| 2.6372 | 28.1124 | 14000 | 2.0094 |
| 1.8545 | 32.1285 | 16000 | 1.5949 |
| 1.4873 | 36.1446 | 18000 | 1.3468 |
| 1.2508 | 40.1606 | 20000 | 1.1876 |
| 1.0889 | 44.1767 | 22000 | 1.0385 |
| 0.9580 | 48.1928 | 24000 | 0.9333 |
| 0.8578 | 52.2088 | 26000 | 0.8454 |
| 0.7791 | 56.2249 | 28000 | 0.7766 |
| 0.7070 | 60.2410 | 30000 | 0.7423 |
| 0.6498 | 64.2570 | 32000 | 0.6968 |
| 0.6035 | 68.2731 | 34000 | 0.6754 |
| 0.5591 | 72.2892 | 36000 | 0.6412 |
| 0.5222 | 76.3052 | 38000 | 0.5862 |
| 0.4908 | 80.3213 | 40000 | 0.5847 |
| 0.4632 | 84.3373 | 42000 | 0.5529 |
| 0.4383 | 88.3534 | 44000 | 0.5341 |
| 0.4163 | 92.3695 | 46000 | 0.5323 |
| 0.3944 | 96.3855 | 48000 | 0.5072 |
| 0.3762 | 100.4016 | 50000 | 0.4913 |
| 0.3596 | 104.4177 | 52000 | 0.4944 |
| 0.3429 | 108.4337 | 54000 | 0.4898 |
| 0.3278 | 112.4498 | 56000 | 0.4626 |
| 0.3164 | 116.4659 | 58000 | 0.4516 |
| 0.3056 | 120.4819 | 60000 | 0.4548 |
| 0.2926 | 124.4980 | 62000 | 0.4538 |
| 0.2825 | 128.5141 | 64000 | 0.4484 |
| 0.2747 | 132.5301 | 66000 | 0.4448 |
| 0.2643 | 136.5462 | 68000 | 0.4394 |
| 0.2554 | 140.5622 | 70000 | 0.4172 |
| 0.2484 | 144.5783 | 72000 | 0.4299 |
| 0.2422 | 148.5944 | 74000 | 0.4298 |
| 0.2345 | 152.6104 | 76000 | 0.4291 |
Framework versions
- Transformers 5.6.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- qbert
- Created
- Apr 24, 2026
- Updated
- May 7, 2026