metadata

base_model: distilbert-base-uncased
datasets:
  - financial_phrasebank
library_name: peft
license: apache-2.0
metrics:
  - accuracy
tags:
  - generated_from_trainer
model-index:
  - name: distilbert-base-uncased-lora-financial-sentiment-analysis
    results: []

distilbert-base-uncased-lora-financial-sentiment-analysis

This model is a fine-tuned version of distilbert-base-uncased on the financial_phrasebank dataset. It achieves the following results on the evaluation set:

Loss: 0.0637
Accuracy: {'accuracy': 0.9779735682819384}

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: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3143	1.0	510	0.0637	{'accuracy': 0.9779735682819384}
0.1253	2.0	1020	0.0722	{'accuracy': 0.973568281938326}
0.0574	3.0	1530	0.0806	{'accuracy': 0.973568281938326}

Framework versions

PEFT 0.11.1
Transformers 4.42.1
Pytorch 2.0.1+cpu
Datasets 2.20.0
Tokenizers 0.19.1