Downloads · 30 days
6
21% of all-time downloads
distilbert-v0
labicquette/distilbert-v0
distilbert-v0 is a token classification model from labicquette. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Parameters
65.2M
261 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors261 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 2, 2024
- Updated
- Apr 2, 2024
- SHA
- 696a9b0a
Try a prompt
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-v0
This model is a fine-tuned version of distilbert/distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4249
- Precision: 0.0860
- Recall: 0.0883
- F1: 0.0792
- Accuracy: 0.1013
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 29 | 2.3644 | 0.0657 | 0.0917 | 0.0241 | 0.1193 |
| No log | 2.0 | 58 | 2.3651 | 0.0979 | 0.0925 | 0.0338 | 0.1195 |
| No log | 3.0 | 87 | 2.3686 | 0.0742 | 0.0923 | 0.0498 | 0.1148 |
| No log | 4.0 | 116 | 2.3718 | 0.0904 | 0.0918 | 0.0619 | 0.1132 |
| No log | 5.0 | 145 | 2.3800 | 0.0893 | 0.0913 | 0.0758 | 0.1082 |
| No log | 6.0 | 174 | 2.3946 | 0.0873 | 0.0915 | 0.0772 | 0.1070 |
| No log | 7.0 | 203 | 2.4064 | 0.0864 | 0.0897 | 0.0780 | 0.1043 |
| No log | 8.0 | 232 | 2.4165 | 0.0872 | 0.0888 | 0.0798 | 0.1019 |
| No log | 9.0 | 261 | 2.4233 | 0.0860 | 0.0885 | 0.0778 | 0.1024 |
| No log | 10.0 | 290 | 2.4249 | 0.0860 | 0.0883 | 0.0792 | 0.1013 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.2.1+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Apr 2, 2024
- Updated
- Apr 2, 2024