Hugging Face's logo

yuriachermann
/
Not-so-bright-AGI-phi-1_5

Question Answering
PEFT
Safetensors
trl
sft
Generated from Trainer
dolly
ipex
max series gpu
Model card Files Community
Not-so-bright-AGI-phi-1_5 / README.md
yuriachermann's picture
yuriachermann
Update README.md
e3da449 verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
  - dolly
  - ipex
  - max series gpu
base_model: microsoft/phi-1_5
datasets:
  - generator
model-index:
  - name: Not-so-bright-AGI-phi-1_5
    results: []
pipeline_tag: question-answering

Not-so-bright-AGI-phi-1_5

This model is a fine-tuned version of microsoft/phi-1_5 on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4005

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 593

Training results

Training Loss Epoch Step Validation Loss
2.7734 0.7921 100 2.5922
2.5468 1.5842 200 2.4699
2.4705 2.3762 300 2.4318
2.4413 3.1683 400 2.4113
2.4318 3.9604 500 2.4005

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.1.0.post0+cxx11.abi
  • Datasets 2.19.1
  • Tokenizers 0.19.1