Downloads · 30 days
8
12% of all-time downloads
gpt2_small_AR_unigram_32768_parallel3-100_42
parallelm/gpt2_small_AR_unigram_32768_parallel3-100_42
gpt2_small_AR_unigram_32768_parallel3-100_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
66
Public
Parameters
110M
13.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors441 MB · 99%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026
- SHA
- 4b816b0e
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_AR_unigram_32768_parallel3-100_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5939
- Accuracy: 0.3653
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 |
|---|---|---|---|---|
| 4.3761 | 1.0 | 7397 | 4.2224 | 0.3053 |
| 4.0466 | 2.0 | 14794 | 3.9378 | 0.3298 |
| 3.8832 | 3.0 | 22191 | 3.8144 | 0.3411 |
| 3.7942 | 4.0 | 29588 | 3.7421 | 0.3489 |
| 3.7303 | 5.0 | 36985 | 3.6961 | 0.3530 |
| 3.6758 | 6.0 | 44382 | 3.6597 | 0.3568 |
| 3.6344 | 7.0 | 51779 | 3.6352 | 0.3601 |
| 3.5989 | 8.0 | 59176 | 3.6151 | 0.3621 |
| 3.5721 | 9.0 | 66573 | 3.6016 | 0.3642 |
| 3.5469 | 10.0 | 73970 | 3.5939 | 0.3653 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026