|
--- |
|
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](https://huggingface.co/microsoft/phi-2) on an [GSM8K dataset](https://huggingface.co/datasets/gsm8k). |
|
|
|
## 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: |
|
|
|
```python |
|
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](https://colab.research.google.com/drive/1mvfoEqc0mwuf8FqrABWt06qwAsU2QrvK). |
|
|
|
### 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](https://huggingface.co/Menouar/phi-2-basic-maths/tensorboard). |
|
|
|
## Evaluation procedure |
|
|
|
The complete Evaluation procedure can be found on my [Notebook](https://colab.research.google.com/drive/1xsdxOm-CgZmLAPFgp8iU9lLFEIIHGiUK). |
|
|
|
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 |