Hugging Face's logo

AdnanRiaz107
/
testm1

PEFT
Safetensors
phi3
Generated from Trainer
custom_code
Model card Files Community
testm1 / README.md
AdnanRiaz107's picture
AdnanRiaz107
testm1
630b6a6 verified
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: microsoft/Phi-3-mini-128k-instruct
model-index:
  - name: testm1
    results: []

testm1

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7114

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-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 1
  • training_steps: 5

Training results

Training Loss Epoch Step Validation Loss
0.7266 1.0 5 0.7114

Framework versions

  • PEFT 0.11.0
  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1