metadata

library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: vinai/PhoGPT-4B-Chat
model-index:
  - name: PhoGPT-7B5-LoRA-v1
    results: []

PhoGPT-7B5-LoRA-v1

This model is a fine-tuned version of vinai/PhoGPT-4B-Chat on the Questions and Answers dataset.

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: 0.0001
train_batch_size: 1
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 250

Training results

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2