ZeroShot-3.3.1-Mistral-7b-Multilanguage-3.2.0

Weni/ZeroShot-3.3.1-Mistral-7b-Multilanguage-3.2.0

ZeroShot-3.3.1-Mistral-7b-Multilanguage-3.2.0 is a machine learning model from Weni. 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

27% of all-time downloads

All-time downloads

Public

Parameters

7.2B

14.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.5 GB · 100%

At a glance

Library: peft
License: apache-2.0
Model type: mistral
Access: Public
Created: Feb 18, 2024
Updated: Feb 21, 2024
SHA: 5909275f

Base models

mistralai/Mistral-7B-Instruct-v0.2

Model card

From the Hugging Face model README

ZeroShot-3.3.1-Mistral-7b-Multilanguage-3.1.0

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3819

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: 8
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7016	0.03	50	0.6892
0.53	0.06	100	0.5066
0.4652	0.09	150	0.4579
0.4299	0.12	200	0.4434
0.4337	0.16	250	0.4362
0.4213	0.19	300	0.4306
0.4207	0.22	350	0.4242
0.4161	0.25	400	0.4199
0.418	0.28	450	0.4170
0.4	0.31	500	0.4134
0.4119	0.34	550	0.4105
0.3993	0.37	600	0.4075
0.394	0.4	650	0.4048
0.389	0.43	700	0.4023
0.391	0.47	750	0.4004
0.4052	0.5	800	0.3978
0.3817	0.53	850	0.3960
0.3781	0.56	900	0.3940
0.3889	0.59	950	0.3920
0.3923	0.62	1000	0.3902
0.3759	0.65	1050	0.3891
0.3825	0.68	1100	0.3878
0.3832	0.71	1150	0.3863
0.3726	0.74	1200	0.3851
0.3826	0.78	1250	0.3844
0.3822	0.81	1300	0.3836
0.3764	0.84	1350	0.3829
0.385	0.87	1400	0.3824
0.3755	0.9	1450	0.3821
0.3621	0.93	1500	0.3820
0.3749	0.96	1550	0.3819
0.3778	0.99	1600	0.3819

Framework versions

PEFT 0.8.2
Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

Library: peft
Type: mistral
License: apache-2.0
Created: Feb 18, 2024
Updated: Feb 21, 2024