Downloads · 30 days
5
5% of all-time downloads
gpt2_small_KO_unigram_65536_parallel10_42
parallelm/gpt2_small_KO_unigram_65536_parallel10_42
gpt2_small_KO_unigram_65536_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
95
Public
Parameters
135M
16.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors542 MB · 98%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Nov 15, 2025
- Updated
- Nov 15, 2025
- SHA
- 52153605
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_KO_unigram_65536_parallel10_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.7875
- Accuracy: 0.3322
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 |
|---|---|---|---|---|
| 7.0481 | 1.0 | 1294 | 5.8227 | 0.2889 |
| 5.7609 | 2.0 | 2588 | 5.3480 | 0.3050 |
| 5.3969 | 3.0 | 3882 | 5.1486 | 0.3144 |
| 5.0853 | 4.0 | 5176 | 5.0227 | 0.3198 |
| 4.9826 | 5.0 | 6470 | 4.9386 | 0.3239 |
| 4.9073 | 6.0 | 7764 | 4.8796 | 0.3273 |
| 4.797 | 7.0 | 9058 | 4.8381 | 0.3290 |
| 4.7477 | 8.0 | 10352 | 4.8120 | 0.3311 |
| 4.7168 | 9.0 | 11646 | 4.7950 | 0.3316 |
| 4.6941 | 10.0 | 12940 | 4.7875 | 0.3322 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Nov 15, 2025
- Updated
- Nov 15, 2025