Hugging Face's logo

regmisaugat59
/
phi-1_5-finetuned

PEFT
TensorBoard
Safetensors
phi
Generated from Trainer
custom_code
Model card Files Metrics Community
phi-1_5-finetuned / README.md
regmisaugat59's picture
regmisaugat59
End of training
ec838e8 verified
preview code
|
raw
history blame contribute delete
1.09 kB
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: microsoft/phi-1_5
model-index:
  - name: phi-1_5-finetuned
    results: []

phi-1_5-finetuned

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 1000

Training results

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2