Downloads · 30 days
4
1% of all-time downloads
gpt2_small_DE_superbpe_81920_parallel10_42
parallelm/gpt2_small_DE_superbpe_81920_parallel10_42
gpt2_small_DE_superbpe_81920_parallel10_42 is a machine learning model from parallelm. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
539
Public
Parameters
148M
18.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors592 MB · 97%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025
- SHA
- 28333994
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. -->
gpt2_small_DE_superbpe_81920_parallel10_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.2746
- Accuracy: 0.2466
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 8.0398 | 1.0 | 1094 | 6.9114 | 0.1760 |
| 6.5829 | 2.0 | 2188 | 6.0974 | 0.2069 |
| 6.0267 | 3.0 | 3282 | 5.7648 | 0.2204 |
| 5.7531 | 4.0 | 4376 | 5.5881 | 0.2283 |
| 5.5801 | 5.0 | 5470 | 5.4717 | 0.2344 |
| 5.4577 | 6.0 | 6564 | 5.3963 | 0.2388 |
| 5.3674 | 7.0 | 7658 | 5.3433 | 0.2424 |
| 5.2974 | 8.0 | 8752 | 5.3055 | 0.2443 |
| 5.2431 | 9.0 | 9846 | 5.2834 | 0.2458 |
| 5.2017 | 10.0 | 10940 | 5.2746 | 0.2466 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025