Downloads · 30 days
4
1% of all-time downloads
gpt2_small_TR_unigram_8192_parallel10_42
parallelm/gpt2_small_TR_unigram_8192_parallel10_42
gpt2_small_TR_unigram_8192_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
304
Public
Parameters
91.4M
11 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors366 MB · 100%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025
- SHA
- ae88dd9d
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_TR_unigram_8192_parallel10_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6688
- Accuracy: 0.3698
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 |
|---|---|---|---|---|
| 5.993 | 1.0 | 1568 | 4.6001 | 0.2798 |
| 4.3498 | 2.0 | 3136 | 4.1638 | 0.3162 |
| 4.15 | 3.0 | 4704 | 3.9793 | 0.3355 |
| 3.9414 | 4.0 | 6272 | 3.8710 | 0.3460 |
| 3.8676 | 5.0 | 7840 | 3.7994 | 0.3537 |
| 3.7678 | 6.0 | 9408 | 3.7521 | 0.3602 |
| 3.7311 | 7.0 | 10976 | 3.7192 | 0.3633 |
| 3.6651 | 8.0 | 12544 | 3.6924 | 0.3661 |
| 3.628 | 9.0 | 14112 | 3.6769 | 0.3691 |
| 3.6054 | 10.0 | 15680 | 3.6688 | 0.3698 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025