Downloads · 30 days
4
2% of all-time downloads
gpt2_small_EN_superbpe_49152_parallel10_42
parallelm/gpt2_small_EN_superbpe_49152_parallel10_42
gpt2_small_EN_superbpe_49152_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
260
Public
Parameters
123M
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors492 MB · 98%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025
- SHA
- b69834b8
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_EN_superbpe_49152_parallel10_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.9983
- Accuracy: 0.2408
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 128
- total_eval_batch_size: 128
- 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 |
|---|---|---|---|---|
| 7.5651 | 1.0 | 1195 | 6.2173 | 0.1797 |
| 6.0614 | 2.0 | 2390 | 5.6091 | 0.2059 |
| 5.6328 | 3.0 | 3585 | 5.3793 | 0.2164 |
| 5.4247 | 4.0 | 4780 | 5.2462 | 0.2230 |
| 5.2888 | 5.0 | 5975 | 5.1586 | 0.2291 |
| 5.1043 | 6.0 | 7170 | 5.0979 | 0.2341 |
| 5.0402 | 7.0 | 8365 | 5.0560 | 0.2359 |
| 4.991 | 8.0 | 9560 | 5.0239 | 0.2393 |
| 4.9508 | 9.0 | 10755 | 5.0064 | 0.2403 |
| 4.9193 | 10.0 | 11950 | 4.9983 | 0.2408 |
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