Downloads · 30 days
3
11% of all-time downloads
tiny_bert_km_20_v1
Hartunka/tiny_bert_km_20_v1
tiny_bert_km_20_v1 is a machine learning model from Hartunka. 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
27
Public
Parameters
33.3M
665 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors133 MB · 99%
At a glance
- Model type
- distilbert
- Access
- Public
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025
- SHA
- 58960f09
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. -->
tiny_bert_km_20_v1
This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-km-20 dataset. It achieves the following results on the evaluation set:
- Loss: 6.7550
- Accuracy: 0.1536
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: 0.0001
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.7928 | 4.1982 | 10000 | 6.8629 | 0.1481 |
| 6.4284 | 8.3963 | 20000 | 6.7387 | 0.1528 |
| 6.2528 | 12.5945 | 30000 | 6.7938 | 0.1534 |
| 6.135 | 16.7926 | 40000 | 6.9908 | 0.1522 |
| 6.0725 | 20.9908 | 50000 | 7.0723 | 0.1516 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1
- Type
- distilbert
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025