DUAL-GPO
/

phi-2-ipo-chatml-lora-i2

alignment-handbook

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

phi-2-ipo-chatml-lora-i2

This model is a fine-tuned version of DUAL-GPO/phi-2-ipo-chatml-lora-20k-40k-i1-merged on the HuggingFaceH4/ultrafeedback_binarized 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: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DUAL-GPO/phi-2-ipo-chatml-lora-i2

Base model

DUAL-GPO/phi-2-ipo-chatml-lora-20k-40k-i1-merged

Adapter

(2)

this model

Dataset used to train DUAL-GPO/phi-2-ipo-chatml-lora-i2