Downloads · 30 days
5
8% of all-time downloads
xlm-roberta-base_ary_corr_5e-06
Shijia/xlm-roberta-base_ary_corr_5e-06
xlm-roberta-base_ary_corr_5e-06 is a text classification model from Shijia. 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
60
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Feb 16, 2024
- Updated
- Feb 16, 2024
- SHA
- 58d18e2e
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. -->
xlm-roberta-base_ary_corr_5e-06
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0259
- Spearman Corr: 0.7521
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-06
- train_batch_size: 32
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
|---|---|---|---|---|
| No log | 0.9 | 200 | 0.0254 | 0.7482 |
| No log | 1.8 | 400 | 0.0271 | 0.7422 |
| 0.006 | 2.7 | 600 | 0.0248 | 0.7442 |
| 0.006 | 3.6 | 800 | 0.0269 | 0.7501 |
| 0.0056 | 4.5 | 1000 | 0.0269 | 0.7512 |
| 0.0056 | 5.41 | 1200 | 0.0259 | 0.7502 |
| 0.005 | 6.31 | 1400 | 0.0254 | 0.7504 |
| 0.005 | 7.21 | 1600 | 0.0255 | 0.7515 |
| 0.0047 | 8.11 | 1800 | 0.0277 | 0.7495 |
| 0.0047 | 9.01 | 2000 | 0.0263 | 0.7467 |
| 0.0047 | 9.91 | 2200 | 0.0264 | 0.7493 |
| 0.0045 | 10.81 | 2400 | 0.0267 | 0.7550 |
| 0.0045 | 11.71 | 2600 | 0.0275 | 0.7497 |
| 0.0043 | 12.61 | 2800 | 0.0282 | 0.7499 |
| 0.0043 | 13.51 | 3000 | 0.0267 | 0.7508 |
| 0.004 | 14.41 | 3200 | 0.0265 | 0.7502 |
| 0.004 | 15.32 | 3400 | 0.0258 | 0.7501 |
| 0.0038 | 16.22 | 3600 | 0.0266 | 0.7519 |
| 0.0038 | 17.12 | 3800 | 0.0261 | 0.7522 |
| 0.0037 | 18.02 | 4000 | 0.0259 | 0.7521 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Feb 16, 2024
- Updated
- Feb 16, 2024