Downloads · 30 days
0
zh_xlmroberta_lora_adapter_1.0
nhankins/zh_xlmroberta_lora_adapter_1.0
zh_xlmroberta_lora_adapter_1.0 is a machine learning model from nhankins. 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 mit.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Feb 9, 2024
Repo size
25.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json17.1 MB · 67%
At a glance
- License
- mit
- Access
- Public
- Created
- Feb 9, 2024
- Updated
- Feb 9, 2024
- SHA
- 4d402bf0
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-lora-text-classification
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: 0.5131
- Precision: 0.7307
- Recall: 1.0
- F1 and accuracy: {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133}
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: 1e-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 and accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 401 | 0.5787 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5822 | 2.0 | 802 | 0.5722 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.586 | 3.0 | 1203 | 0.5636 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5504 | 4.0 | 1604 | 0.5513 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5661 | 5.0 | 2005 | 0.5451 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5661 | 6.0 | 2406 | 0.5332 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5562 | 7.0 | 2807 | 0.5329 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5354 | 8.0 | 3208 | 0.5252 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5575 | 9.0 | 3609 | 0.5149 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
| 0.5301 | 10.0 | 4010 | 0.5131 | 0.7307 | 1.0 | {'accuracy': 0.7306733167082294, 'f1': 0.8443804034582133} |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- License
- mit
- Created
- Feb 9, 2024
- Updated
- Feb 9, 2024