ZeroShot-3.3.24-Mistral-7b-Multilanguage-3.2.0

Weni/ZeroShot-3.3.24-Mistral-7b-Multilanguage-3.2.0

ZeroShot-3.3.24-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

45% of all-time downloads

All-time downloads

Public

Parameters

7.2B

17.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.9 GB · 100%

At a glance

Library: peft
License: apache-2.0
Model type: mistral
Access: Public
Created: Mar 5, 2024
Updated: Mar 5, 2024
SHA: 54d6e08a

Base models

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

Model card

From the Hugging Face model README

ZeroShot-3.3.24-Mistral-7b-Multilanguage-3.2.0

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: 0.1109

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: 8
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: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1175	0.06	100	0.1109
0.117	0.12	200	0.1318
0.1596	0.19	300	0.1316
0.4487	0.25	400	0.2081
1.0524	0.31	500	7.3647
0.0	0.37	600	nan
0.0	0.43	700	nan
0.0	0.5	800	nan
0.0	0.56	900	nan
0.0	0.62	1000	nan
0.0	0.68	1100	nan
0.0	0.74	1200	nan
0.0	0.81	1300	nan
0.0	0.87	1400	nan
0.0	0.93	1500	nan
0.0	0.99	1600	nan
0.0	1.05	1700	nan
0.0	1.12	1800	nan
9.5008	1.18	1900	nan
0.0	1.24	2000	nan
0.0	1.3	2100	nan
0.0	1.36	2200	nan
0.0	1.43	2300	nan
0.0	1.49	2400	nan
0.0	1.55	2500	nan
0.0	1.61	2600	nan
0.0	1.67	2700	nan
0.0	1.74	2800	nan
0.0	1.8	2900	nan
0.0	1.86	3000	nan
0.0	1.92	3100	nan
0.0	1.98	3200	nan
0.0	2.05	3300	nan
0.0	2.11	3400	nan
0.0	2.17	3500	nan
0.0	2.23	3600	nan
0.0	2.29	3700	nan
0.0	2.36	3800	nan
0.0	2.42	3900	nan
0.0	2.48	4000	nan
0.0	2.54	4100	nan
0.0	2.6	4200	nan
0.0	2.67	4300	nan
0.0	2.73	4400	nan
0.0	2.79	4500	nan
0.0	2.85	4600	nan
0.0	2.91	4700	nan
0.0	2.98	4800	nan

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Library: peft
Type: mistral
License: apache-2.0
Created: Mar 5, 2024
Updated: Mar 5, 2024