neo_7B_sft_v0_1_plus-dpo-iter2-beta0_1

This model is a fine-tuned version of /ML-A100/team/mm/zhangge/iterativeDPO/data/model/full/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3 on the /ML-A100/team/mm/zhangge/iterativeDPO/data/dataset/generate/neo_7B_sft_v0_1_plus-dpo-iter1-beta0_3-generate-chosen-rejected-reward 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: 3
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 128
• total_train_batch_size: 384
• total_eval_batch_size: 1024
• 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 4.39.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2