Downloads · 30 days
10
25% of all-time downloads
outputs
yihong-gongzi/outputs
outputs is a token classification model from yihong-gongzi. Use it when you need labels on individual words, such as names. 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
40
Public
Parameters
124M
496 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors496 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Mar 23, 2025
- Updated
- Mar 23, 2025
- SHA
- e70ddf7b
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. -->
outputs
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2428
- Precision: 0.4001
- Recall: 0.4250
- F1: 0.4122
- Accuracy: 0.9284
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: 2
- eval_batch_size: 2
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4193 | 1.0 | 161 | 0.3617 | 0.2254 | 0.0814 | 0.1196 | 0.9191 |
| 0.277 | 2.0 | 322 | 0.2614 | 0.3917 | 0.2375 | 0.2957 | 0.9273 |
| 0.2348 | 3.0 | 483 | 0.2318 | 0.3973 | 0.3461 | 0.3700 | 0.9278 |
| 0.1894 | 4.0 | 644 | 0.2259 | 0.4120 | 0.3656 | 0.3874 | 0.9301 |
| 0.1643 | 5.0 | 805 | 0.2334 | 0.3633 | 0.4267 | 0.3925 | 0.9238 |
| 0.161 | 6.0 | 966 | 0.2254 | 0.3885 | 0.4118 | 0.3998 | 0.9273 |
| 0.1289 | 7.0 | 1127 | 0.2446 | 0.3706 | 0.4750 | 0.4164 | 0.9211 |
| 0.121 | 8.0 | 1288 | 0.2437 | 0.3739 | 0.4416 | 0.4049 | 0.9239 |
| 0.1075 | 9.0 | 1449 | 0.2428 | 0.4001 | 0.4250 | 0.4122 | 0.9284 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Mar 23, 2025
- Updated
- Mar 23, 2025