metadata

license: mit
base_model: BAAI/bge-small-zh-v1.5
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: sft-bge-bert24m-to-sentiment
    results: []
pipeline_tag: text-classification
datasets:
  - tyqiangz/multilingual-sentiments
widget:
  - text: 王女士最近和老板吵了一架，似乎心情很沮丧。

sft-bge-bert24m-to-sentiment

This model is a fine-tuned version of BAAI/bge-small-zh-v1.5 on a dataset tyqiangz/multilingual-sentiment(name = 'chinese'). It achieves the following results on the evaluation set:

Loss: 0.5434
Accuracy: 0.779

Usage for the Model

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="dumyy/sft-bge-bert24m-to-sentiment")

result = pipe("我最近遇到了很糟糕的事，让我异常郁闷。")

print(result)

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.534	1.0	3750	0.5576	0.7653
0.4898	2.0	7500	0.5434	0.779

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2