metadata
language:
- en
license: mit
base_model: microsoft/deberta-v3-xsmall
tags:
- nycu-112-2-datamining-hw2
- generated_from_trainer
datasets:
- DandinPower/review_onlytitleandtext
metrics:
- accuracy
model-index:
- name: deberta-v3-xsmall-otat-recommened-hp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: DandinPower/review_onlytitleandtext
type: DandinPower/review_onlytitleandtext
metrics:
- name: Accuracy
type: accuracy
value: 0.6391428571428571
deberta-v3-xsmall-otat-recommened-hp
This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the DandinPower/review_onlytitleandtext dataset. It achieves the following results on the evaluation set:
- Loss: 1.0799
- Accuracy: 0.6391
- Macro F1: 0.6372
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.97 | 1.14 | 500 | 0.9598 | 0.5957 | 0.5847 |
| 0.8311 | 2.29 | 1000 | 0.8698 | 0.6371 | 0.6267 |
| 0.7452 | 3.43 | 1500 | 0.8271 | 0.6457 | 0.6471 |
| 0.678 | 4.57 | 2000 | 0.8802 | 0.6421 | 0.6359 |
| 0.6161 | 5.71 | 2500 | 0.9048 | 0.6457 | 0.6463 |
| 0.5784 | 6.86 | 3000 | 0.9604 | 0.6439 | 0.6452 |
| 0.5068 | 8.0 | 3500 | 1.0170 | 0.6453 | 0.6452 |
| 0.4247 | 9.14 | 4000 | 1.0799 | 0.6391 | 0.6372 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2