metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
- pytorch
base_model: microsoft/phi-2
model-index:
- name: phi-2-basic-maths
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
name: normalized accuracy
value: 62.03071672354948
source:
name: Open LLM Leaderboard
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
name: normalized accuracy
value: 84.35570603465445
source:
name: Open LLM Leaderboard
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
datasets:
- gsm8k
source:
name: Open LLM Leaderboard
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Menouar/phi-2-basic-maths
language:
- en
pipeline_tag: text-generation
phi-2-basic-maths
This model is a fine-tuned version of microsoft/phi-2 on an GSM8K dataset.
Model Description
The objective of this model is to evaluate Phi-2's ability to provide correct solutions to reasoning problems after fine-tuning. This model was trained using techniques such as TRL, LoRA quantization, and Flash Attention.
To test it, you can use the following code:
import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, pipeline
# Specify the model ID
peft_model_id = "Menouar/phi-2-basic-maths"
# Load Model with PEFT adapter
model = AutoPeftModelForCausalLM.from_pretrained(
peft_model_id,
device_map="auto",
torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
Training procedure
The complete training procedure can be found on my Notebook.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 42
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 84
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 30
Training results
The training results can be found on Tensoboard.
Evaluation procedure
The complete Evaluation procedure can be found on my Notebook.
Accuracy: 36.16%
Unclear answers: 7.81%
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1