metadata

license: apache-2.0
tags:
  - generated_from_trainer
base_model: distilbert-base-uncased
model-index:
  - name: uzb-senAnalys
    results: []

uzbek-sentiment-analysis

It achieves the following results on the evaluation set:

eval_loss: 0.6374
eval_accuracy: {'accuracy': 0.7862348178137651}
eval_f1score: {'f1': 0.7880364308572618}
eval_runtime: 7.593
eval_samples_per_second: 162.65
eval_steps_per_second: 20.414
step: 0

Model description

uzbek-sentiment-analysis modelidan foydalanish.

from transformers import pipeline

pipe = pipeline('sentimennt-analysis', model='ai-nightcoder/uzbek-sentiment-analysis-v5')

text = "bu ovqatni men juda ham yaxshi ko'raman."
pipe(text)[0]['label']

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 864
num_epochs: 7

Framework versions

Transformers 4.40.1
Pytorch 2.4.0.dev20240416+cu121
Datasets 1.18.3
Tokenizers 0.19.1