Hugging Face's logo

SamChen888
/
Mistral-7B-Finetune-RDE

PEFT
Safetensors
t5
llama-factory
lora
Generated from Trainer
Model card Files Community
Mistral-7B-Finetune-RDE / README.md
SamChen888's picture
SamChen888
Upload folder using huggingface_hub
f0712ae verified
preview code
|
raw
history blame
1.22 kB
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: peft
license: other
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: train_mistral
    results: []

train_mistral

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the treino_pt_rde 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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3.0

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.3.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1