Downloads · 30 days
19
13% of all-time downloads
gpt-mha-SwiGLU
kaanino/gpt-mha-SwiGLU
gpt-mha-SwiGLU is a machine learning model from kaanino. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
147
Public
Parameters
6.9M
302 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.4 MB · 88%
At a glance
- Library
- transformers
- Model type
- gpt
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- 23735b20
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. -->
gpt-mha-SwiGLU
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.0675
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: 0.0003
- train_batch_size: 128
- eval_batch_size: 128
- seed: 20
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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: cosine
- lr_scheduler_warmup_steps: 107
- training_steps: 1071
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.4965 | 0.0595 | 107 | 9.1925 |
| 7.7058 | 0.1190 | 214 | 7.6048 |
| 7.0658 | 0.1786 | 321 | 7.0129 |
| 6.7174 | 0.2381 | 428 | 6.6475 |
| 6.4503 | 0.2976 | 535 | 6.3979 |
| 6.2793 | 0.3571 | 642 | 6.2361 |
| 6.1853 | 0.4166 | 749 | 6.1396 |
| 6.1286 | 0.4762 | 856 | 6.0895 |
| 6.1144 | 0.5357 | 963 | 6.0705 |
| 6.1000 | 0.5952 | 1070 | 6.0675 |
| 6.1000 | 0.5957 | 1071 | 6.0675 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Library
- transformers
- Type
- gpt
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026