metadata
language:
- en
license: mit
base_model: microsoft/deberta-v3-base
tags:
- nycu-112-2-datamining-hw2
- generated_from_trainer
datasets:
- DandinPower/review_onlytitleandtext
metrics:
- accuracy
model-index:
- name: deberta-v3-base-otat
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: DandinPower/review_onlytitleandtext
type: DandinPower/review_onlytitleandtext
metrics:
- name: Accuracy
type: accuracy
value: 0.6360357142857143
deberta-v3-base-otat
This model is a fine-tuned version of microsoft/deberta-v3-base on the DandinPower/review_onlytitleandtext dataset. It achieves the following results on the evaluation set:
- Loss: 1.5029
- Accuracy: 0.6360
- Macro F1: 0.6367
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: 4.5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.9961 | 0.57 | 500 | 0.9958 | 0.5675 | 0.5638 |
| 0.9267 | 1.14 | 1000 | 0.9776 | 0.5814 | 0.5727 |
| 0.9086 | 1.71 | 1500 | 1.1673 | 0.5709 | 0.5355 |
| 0.744 | 2.29 | 2000 | 0.9788 | 0.6325 | 0.6267 |
| 0.7131 | 2.86 | 2500 | 0.9493 | 0.6219 | 0.6203 |
| 0.5815 | 3.43 | 3000 | 0.9966 | 0.6224 | 0.6259 |
| 0.5434 | 4.0 | 3500 | 1.1400 | 0.6336 | 0.6326 |
| 0.3162 | 4.57 | 4000 | 1.5029 | 0.6360 | 0.6367 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2