Hugging Face's logo

bala3040
/
XPFaculty-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
XPFaculty-ft / README.md
bala3040's picture
bala3040
bala3040/qa_bot
b03ab60 verified
preview code
|
raw
history blame contribute delete
1.62 kB
metadata
library_name: peft
license: apache-2.0
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
tags:
  - generated_from_trainer
model-index:
  - name: XPFaculty-ft
    results: []

XPFaculty-ft

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5351

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.8113 1.0 75 1.5410
1.3656 2.0 150 1.5351

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3