README.md

metadata

base_model: mistralai/Mistral-7B-v0.1
tags:
  - alignment-handbook
  - trl
  - orpo
  - generated_from_trainer
  - trl
  - orpo
  - generated_from_trainer
  - entity linking
datasets:
  - daisd-ai/anydef-kilt-tasks
model-index:
  - name: anydef-orpo
    results: []
license: apache-2.0
inference: false

anydef-orpo

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the daisd-ai/anydef-kilt-tasks dataset.

Find out about Model description, Intended uses & limitations and Training and evaluation data on our github.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• 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: inverse_sqrt
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2