Hugging Face's logo

Luongdzung
/
Qlora_500_last_question_wikiqa_seed_13

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Qlora_500_last_question_wikiqa_seed_13 / README.md
Luongdzung's picture
Luongdzung
End of training
981c886 verified
preview code
|
raw
history blame
1.49 kB
metadata
base_model: vlsp-2023-vllm/hoa-1b4
library_name: peft
license: bigscience-bloom-rail-1.0
tags:
  - generated_from_trainer
model-index:
  - name: Qlora_500_last_question_wikiqa_seed_13
    results: []

Qlora_500_last_question_wikiqa_seed_13

This model is a fine-tuned version of vlsp-2023-vllm/hoa-1b4 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5324

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
0.9487 1.0 50 0.7875
0.8394 2.0 100 0.5958
0.4678 3.0 150 0.5324

Framework versions

  • PEFT 0.13.0
  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1