wayang-7b-sft-lora / README.md
Rifky's picture
Update README.md
5013905 verified
metadata
license: cc-by-4.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
datasets:
  - generator
model-index:
  - name: wayang-7b-sft-lora
    results: []
language:
  - id

wayang-7b-sft-lora

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4011

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • total_eval_batch_size: 4
  • 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

Training Loss Epoch Step Validation Loss
1.3775 1.0 19328 1.4011

Framework versions

  • PEFT 0.7.1
  • Transformers 4.38.2
  • Pytorch 2.1.0a0+32f93b1
  • Datasets 2.14.6
  • Tokenizers 0.15.2