mistral_finetuned_for_QA

Tien09/mistral_finetuned_for_QA

mistral_finetuned_for_QA is a machine learning model from Tien09. 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 apache-2.0.

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

Downloads · 30 days

32% of all-time downloads

All-time downloads

Public

Repo size

8.9 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors8.4 MB · 78%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 14, 2024
Updated: Mar 14, 2024
SHA: 061009aa

Base models

mistralai/Mistral-7B-Instruct-v0.1

Model card

From the Hugging Face model README

mistral_finetuned_for_QA

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5183

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: 0.0002
train_batch_size: 2
eval_batch_size: 2
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_steps: 2
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6888	0.94	11	0.5848
0.5173	1.96	23	0.5344
0.4767	2.98	35	0.5221
0.4543	4.0	47	0.5188
0.4532	4.68	55	0.5183

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.14.7
Tokenizers 0.15.2

Library: peft
License: apache-2.0
Created: Mar 14, 2024
Updated: Mar 14, 2024