Hugging Face's logo

sert121
/
dpo_run_medllama

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
dpo_run_medllama / README.md
sert121's picture
sert121
dpo_run_medllama
0645f7e verified
preview code
|
raw
history blame contribute delete
1.48 kB
metadata
base_model: instruction-pretrain/medicine-Llama3-8B
library_name: peft
license: llama3
tags:
  - trl
  - dpo
  - generated_from_trainer
model-index:
  - name: dpo_run_medllama
    results: []

Visualize in Weights & Biases

dpo_run_medllama

This model is a fine-tuned version of instruction-pretrain/medicine-Llama3-8B on an unknown 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: 8e-06
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 6
  • total_train_batch_size: 12
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 150
  • num_epochs: 3.0

Training results

Framework versions

  • PEFT 0.13.0
  • Transformers 4.42.0
  • Pytorch 2.4.1+cu121
  • Datasets 2.16.1
  • Tokenizers 0.19.1