metadata

license: other
base_model: /data/user/chengrui/project/mergekit/Phi-3-mini-128k-instruct
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: phi3-chinese-orpo
    results: []

phi3-chinese-orpo

This model is a fine-tuned version of /data/user/chengrui/project/mergekit/Phi-3-mini-128k-instruct on the dpo_mix_en and the dpo_mix_zh datasets.

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: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 6
gradient_accumulation_steps: 8
total_train_batch_size: 48
total_eval_batch_size: 6
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 20
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.40.0
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.19.1