Edit model card

tinyllama-1.1b-chat-v1.0-arena-hh-dpo

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the HuggingFaceH4/hh-rlhf-h4 and the data/chatbot_arena_conversations datasets. It achieves the following results on the evaluation set:

  • Loss: 0.6741
  • Rewards/chosen: -0.5672
  • Rewards/rejected: -0.6232
  • Rewards/accuracies: 0.5643
  • Rewards/margins: 0.0561
  • Logps/rejected: -221.2706
  • Logps/chosen: -218.0917
  • Logits/rejected: -2.3759
  • Logits/chosen: -2.3758

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
Downloads last month
7
Safetensors
Model size
1.1B 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 NicholasCorrado/tinyllama-1.1b-chat-v1.0-arena-hh-dpo

Finetuned
(147)
this model

Dataset used to train NicholasCorrado/tinyllama-1.1b-chat-v1.0-arena-hh-dpo