metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Noisy10per-deberta-v3-small-Label_B-768-epochs-9
results: []
Noisy10per-deberta-v3-small-Label_B-768-epochs-9
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1297
- Accuracy: 0.9854
- F1: 0.9854
- Precision: 0.9856
- Recall: 0.9854
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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0764 | 0.9995 | 1066 | 0.1081 | 0.9730 | 0.9731 | 0.9733 | 0.9730 |
| 0.083 | 1.9993 | 2132 | 0.1059 | 0.9763 | 0.9762 | 0.9770 | 0.9763 |
| 0.0474 | 2.9991 | 3198 | 0.0775 | 0.9833 | 0.9833 | 0.9834 | 0.9833 |
| 0.0028 | 3.9998 | 4265 | 0.1005 | 0.9818 | 0.9818 | 0.9821 | 0.9818 |
| 0.0025 | 4.9995 | 5331 | 0.1092 | 0.9841 | 0.9842 | 0.9843 | 0.9841 |
| 0.0287 | 5.9993 | 6397 | 0.1633 | 0.9820 | 0.9821 | 0.9827 | 0.9820 |
| 0.0085 | 6.9991 | 7463 | 0.1640 | 0.9814 | 0.9814 | 0.9818 | 0.9814 |
| 0.001 | 7.9998 | 8530 | 0.1297 | 0.9854 | 0.9854 | 0.9856 | 0.9854 |
| 0.0 | 8.9977 | 9594 | 0.1368 | 0.9851 | 0.9852 | 0.9853 | 0.9851 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3