metadata
language:
- en
license: mit
base_model: microsoft/deberta-v3-xsmall
tags:
- nycu-112-2-datamining-hw2
- generated_from_trainer
datasets:
- DandinPower/review_cleanonlytitleandtext
metrics:
- accuracy
model-index:
- name: deberta-v3-xsmall-cotat-recommened-hp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: DandinPower/review_cleanonlytitleandtext
type: DandinPower/review_cleanonlytitleandtext
metrics:
- name: Accuracy
type: accuracy
value: 0.6262857142857143
deberta-v3-xsmall-cotat-recommened-hp
This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the DandinPower/review_cleanonlytitleandtext dataset. It achieves the following results on the evaluation set:
- Loss: 0.8783
- Accuracy: 0.6263
- Macro F1: 0.6285
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: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 1.61 | 0.4571 | 100 | 1.6076 | 0.22 | 0.1631 |
| 1.5063 | 0.9143 | 200 | 1.2854 | 0.4094 | 0.2942 |
| 1.2016 | 1.3714 | 300 | 1.0481 | 0.5529 | 0.5311 |
| 1.0219 | 1.8286 | 400 | 0.9338 | 0.6093 | 0.6020 |
| 0.9362 | 2.2857 | 500 | 0.8919 | 0.6261 | 0.6239 |
| 0.9097 | 2.7429 | 600 | 0.8783 | 0.6263 | 0.6285 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1