metadata

license: cc-by-nc-4.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
base_model: Edentns/DataVortexS-10.7B-dpo-v1.11
model-index:
  - name: best-one
    results: []

best-one

This model is a fine-tuned version of Edentns/DataVortexS-10.7B-dpo-v1.11 on the generator 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: 0.0002
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: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 4
mixed_precision_training: Native AMP

Framework versions

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