Hugging Face's logo

Oliver2019
/
Experiment-QA-Breeze-7B-Instruct-v1_0

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Experiment-QA-Breeze-7B-Instruct-v1_0 / README.md
Oliver2019's picture
Oliver2019
Model save
f775b6f verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
model-index:
  - name: Experiment-QA-Breeze-7B-Instruct-v1_0
    results: []

Experiment-QA-Breeze-7B-Instruct-v1_0

This model is a fine-tuned version of MediaTek-Research/Breeze-7B-Instruct-v1_0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7361

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.3943 1.0 27 1.9839
1.9857 2.0 54 1.8182
1.8169 3.0 81 1.7600
1.6758 4.0 108 1.7318
1.636 5.0 135 1.7330
1.5205 6.0 162 1.7361

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.1
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.15.0