Edit model card

Built with Axolotl

openhermes-2_5-dpo-no-robots

This model is a RL fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on a preference dataset derived from HuggingFace's no robots dataset using DPO.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-07
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 20
  • training_steps: 408

Training results

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
7
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for openaccess-ai-collective/openhermes-2_5-dpo-no-robots

Finetuned
(71)
this model
Merges
1 model

Datasets used to train openaccess-ai-collective/openhermes-2_5-dpo-no-robots

Space using openaccess-ai-collective/openhermes-2_5-dpo-no-robots 1