Downloads · 30 days
15
6% of all-time downloads
test_trainer
Christiyke/test_trainer
test_trainer is a text classification model from Christiyke. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
267
Public
Repo size
59 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Sep 5, 2023
- Updated
- Oct 22, 2023
- SHA
- cbfe87e3
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. -->
test_trainer
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7844
- F1: 0.6571
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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.8892 | 0.5 | 500 | 0.8333 | 0.5658 |
| 0.8055 | 1.0 | 1000 | 0.7958 | 0.6600 |
| 0.7423 | 1.5 | 1500 | 0.7959 | 0.6586 |
| 0.7837 | 2.0 | 2000 | 0.8116 | 0.6463 |
| 0.7637 | 2.5 | 2500 | 0.8117 | 0.6402 |
| 0.7462 | 3.0 | 3000 | 0.7844 | 0.6571 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Sep 5, 2023
- Updated
- Oct 22, 2023