Hugging Face's logo

MichaelR207
/
mistral-sft-7b-dpo-qlora

PEFT
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files Community
mistral-sft-7b-dpo-qlora / README.md
MichaelR207's picture
MichaelR207
End of training
6b46192 verified
preview code
|
raw history blame contribute delete
No virus
1.75 kB
metadata
license: mit
library_name: peft
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
base_model: HuggingFaceH4/mistral-7b-sft-beta
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: mistral-sft-7b-dpo-qlora
    results: []

mistral-sft-7b-dpo-qlora

This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6936
  • Rewards/chosen: 0.0005
  • Rewards/rejected: 0.0001
  • Rewards/accuracies: 0.6875
  • Rewards/margins: 0.0003
  • Logps/rejected: -122.9776
  • Logps/chosen: -86.4464
  • Logits/rejected: -3.0453
  • Logits/chosen: -2.9824

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-06
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 221
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Framework versions

  • PEFT 0.7.1
  • Transformers 4.38.2
  • Pytorch 2.2.1
  • Datasets 2.14.6
  • Tokenizers 0.15.2