Hugging Face's logo

nitinaggarwal12
/
phi-1_5-finetuned-gsm8k-v2

PEFT
TensorBoard
Safetensors
phi
Generated from Trainer
Model card Files Metrics Community
phi-1_5-finetuned-gsm8k-v2 / README.md
nitinaggarwal12's picture
nitinaggarwal12
End of training
d750f4e verified
preview code
|
raw
history blame
1.14 kB
metadata
base_model: microsoft/phi-1_5
library_name: peft
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: phi-1_5-finetuned-gsm8k-v2
    results: []

phi-1_5-finetuned-gsm8k-v2

This model is a fine-tuned version of microsoft/phi-1_5 on the None 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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 1000

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 1.13.1+cu117
  • Datasets 2.20.0
  • Tokenizers 0.19.1