kangoroo-no-subgraph-phi-3-mini-LoRA-full

sazirarrwth99/kangoroo-no-subgraph-phi-3-mini-LoRA-full

kangoroo-no-subgraph-phi-3-mini-LoRA-full is a machine learning model from sazirarrwth99. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

126

Public

Repo size

36.2 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors35.7 MB · 94%

At a glance

Library: peft
License: mit
Access: Public
Created: Aug 25, 2024
Updated: Aug 25, 2024
SHA: d950b9d5

Base models

microsoft/Phi-3.5-mini-instruct

Model card

From the Hugging Face model README

kangoroo-no-subgraph-phi-3-mini-LoRA-full

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5046

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: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2973	0.6088	100	0.9424
0.7426	1.2177	200	0.5989
0.535	1.8265	300	0.5046

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Library: peft
License: mit
Created: Aug 25, 2024
Updated: Aug 25, 2024