metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert-base-uncased-finetuned-LoRA-RTE
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.6642599277978339
bert-base-uncased-finetuned-lora-rte
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.6643
- trainable model parameters: 296450
- all model parameters: 109780228
- percentage of trainable model parameters: 0.27%
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-04
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- rank: 8
- lora_alpha: 32
- lora_dropout: 0.05
- num_epochs: 3