Downloads · 30 days
8
5% of all-time downloads
gpt2_small_KO_unigram_81920_parallel10_42
parallelm/gpt2_small_KO_unigram_81920_parallel10_42
gpt2_small_KO_unigram_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
159
Public
Parameters
148M
18.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors592 MB · 98%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Nov 16, 2025
- SHA
- 1fb26316
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_81920_parallel10_42
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.8512
- Accuracy: 0.3341
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 |
|---|---|---|---|---|
| 7.134 | 1.0 | 1275 | 5.8988 | 0.2910 |
| 5.8309 | 2.0 | 2550 | 5.4159 | 0.3084 |
| 5.4644 | 3.0 | 3825 | 5.2114 | 0.3166 |
| 5.1512 | 4.0 | 5100 | 5.0901 | 0.3227 |
| 5.0461 | 5.0 | 6375 | 5.0041 | 0.3264 |
| 4.9701 | 6.0 | 7650 | 4.9424 | 0.3291 |
| 4.9075 | 7.0 | 8925 | 4.9031 | 0.3312 |
| 4.8113 | 8.0 | 10200 | 4.8749 | 0.3328 |
| 4.7772 | 9.0 | 11475 | 4.8583 | 0.3337 |
| 4.7547 | 10.0 | 12750 | 4.8512 | 0.3341 |
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