Downloads · 30 days
2
10% of all-time downloads
WITHINAPPS_NDD-claroline_test-content-CwAdj_EntireRepresentations
lgk03/WITHINAPPS_NDD-claroline_test-content-CwAdj_EntireRepresentations
WITHINAPPS_NDD-claroline_test-content-CwAdj_EntireRepresentations is a machine learning model from lgk03. 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
20
Public
Parameters
67M
2.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Aug 6, 2024
- Updated
- Aug 6, 2024
- SHA
- 64e289bd
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. -->
WITHINAPPS_NDD-claroline_test-content-CwAdj_EntireRepresentations
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1202
- Accuracy: 0.9553
- F1: 0.9565
- Precision: 0.9594
- Recall: 0.9553
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 0.9888 | 55 | 0.5829 | 0.5028 | 0.5553 | 0.8120 | 0.5028 |
| No log | 1.9955 | 111 | 0.4598 | 0.6474 | 0.6918 | 0.8676 | 0.6474 |
| No log | 2.9843 | 166 | 0.3860 | 0.7400 | 0.7725 | 0.8795 | 0.7400 |
| No log | 3.9910 | 222 | 0.3183 | 0.8039 | 0.8255 | 0.8888 | 0.8039 |
| No log | 4.9978 | 278 | 0.2433 | 0.8354 | 0.8521 | 0.9015 | 0.8354 |
| No log | 5.9865 | 333 | 0.1958 | 0.9133 | 0.9184 | 0.9319 | 0.9133 |
| No log | 6.9933 | 389 | 0.1518 | 0.9294 | 0.9329 | 0.9424 | 0.9294 |
| No log | 8.0 | 445 | 0.1309 | 0.9463 | 0.9481 | 0.9530 | 0.9463 |
| 0.3353 | 8.9888 | 500 | 0.1233 | 0.9561 | 0.9571 | 0.9594 | 0.9561 |
| 0.3353 | 9.8876 | 550 | 0.1202 | 0.9553 | 0.9565 | 0.9594 | 0.9553 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- distilbert
- License
- apache-2.0
- Created
- Aug 6, 2024
- Updated
- Aug 6, 2024