Hugging Face's logo

ananyarn
/
new_python_convert

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
new_python_convert / README.md
ananyarn's picture
ananyarn
End of training
a046d29 verified
preview code
|
raw
history blame contribute delete
1.72 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
model-index:
  - name: new_python_convert
    results: []

new_python_convert

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

  • Loss: 0.5715

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • training_steps: 250

Training results

Training Loss Epoch Step Validation Loss
0.835 0.09 50 0.7085
0.6458 0.18 100 0.6176
0.5822 0.27 150 0.5697
0.5627 0.36 200 0.5664
0.5495 0.44 250 0.5715

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0
  • Datasets 2.16.1
  • Tokenizers 0.15.1