Downloads · 30 days
9
9% of all-time downloads
distilbert-multi-finetuning
theunmans/distilbert-multi-finetuning
distilbert-multi-finetuning is a machine learning model from theunmans. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
96
Public
Parameters
135M
2.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors542 MB · 98%
At a glance
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Aug 22, 2024
- Updated
- Aug 23, 2024
- SHA
- 0e1818e6
Base models
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. -->
distilbert-multi-finetuning
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8003
- Accuracy: 0.8017
- F1: 0.7994
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.9844 | 1.0 | 65741 | 1.0179 | 0.7508 | 0.7414 |
| 1.0829 | 2.0 | 131482 | 0.9029 | 0.7744 | 0.7687 |
| 0.5999 | 3.0 | 197223 | 0.8359 | 0.7900 | 0.7870 |
| 0.4741 | 4.0 | 262964 | 0.8003 | 0.8017 | 0.7994 |
| 0.7136 | 5.0 | 328705 | 0.8279 | 0.8060 | 0.8041 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- distilbert
- License
- apache-2.0
- Created
- Aug 22, 2024
- Updated
- Aug 23, 2024