flash_attention_fine-tuned_mistral

shakhizat/flash_attention_fine-tuned_mistral

flash_attention_fine-tuned_mistral is a machine learning model from shakhizat. 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

37% of all-time downloads

All-time downloads

Public

Repo size

114 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors113 MB · 96%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Jun 2, 2024
Updated: Jun 3, 2024
SHA: 09d0ebf5

Base models

mistralai/Mistral-7B-v0.1

Model card

From the Hugging Face model README

flash_attention_fine-tuned_mistral

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

Loss: 1.1909

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: 1
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.01
training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0020	10	1.2457
No log	0.0041	20	1.2098
1.3368	0.0061	30	1.2134
1.3368	0.0081	40	1.2185
1.2308	0.0102	50	1.2187
1.2308	0.0122	60	1.2190
1.2308	0.0142	70	1.2074
1.2921	0.0163	80	1.2018
1.2921	0.0183	90	1.1937
1.2655	0.0203	100	1.1909

Framework versions

PEFT 0.11.1
Transformers 4.41.1
Pytorch 2.2.0
Datasets 2.19.1
Tokenizers 0.19.1

Library: peft
License: apache-2.0
Created: Jun 2, 2024
Updated: Jun 3, 2024