metadata

library_name: transformers
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - data/rlced_conifer
model-index:
  - name: rlced-conifer-zephyr-7b-dpo-full
    results: []

rlced-conifer-zephyr-7b-dpo-full

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the data/rlced_conifer dataset. It achieves the following results on the evaluation set:

Loss: 0.1691
Rewards/chosen: -2.9092
Rewards/rejected: -8.6906
Rewards/accuracies: 0.9240
Rewards/margins: 5.7814
Logps/rejected: -1311.8641
Logps/chosen: -712.8596
Logits/rejected: 0.8491
Logits/chosen: -0.7188

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-07
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
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

Transformers 4.44.1
Pytorch 2.1.2+cu121
Datasets 2.21.0
Tokenizers 0.19.1