fine-tuned_mistral

blueton/fine-tuned_mistral

fine-tuned_mistral is a machine learning model from blueton. 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

33% 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 · 98%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Jul 28, 2024
Updated: Jul 28, 2024
SHA: 69afbf50

Base models

mistralai/Mistral-7B-v0.1

Model card

From the Hugging Face model README

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: 1.1406

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 6
total_train_batch_size: 24
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	0.0244	10	1.1972
No log	0.0487	20	1.1690
1.1917	0.0731	30	1.1567
1.1917	0.0975	40	1.1545
1.1251	0.1219	50	1.1524
1.1251	0.1462	60	1.1490
1.1251	0.1706	70	1.1476
1.1164	0.1950	80	1.1454
1.1164	0.2193	90	1.1425
1.1268	0.2437	100	1.1406

Framework versions

PEFT 0.12.0
Transformers 4.43.3
Pytorch 2.2.0
Datasets 2.20.0
Tokenizers 0.19.1

Library: peft
License: apache-2.0
Created: Jul 28, 2024
Updated: Jul 28, 2024