mistral-7b-instruct-autextification2024

acmc/mistral-7b-instruct-autextification2024

mistral-7b-instruct-autextification2024 is a machine learning model from acmc. 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

6% of all-time downloads

All-time downloads

100

Public

Repo size

110 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors109 MB · 98%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 28, 2024
Updated: Mar 28, 2024
SHA: 1208d454

Base models

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

Model card

From the Hugging Face model README

mistral-7b-instruct-autextification2024

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: 1.8230

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: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.7076	0.0	10	2.0916
1.54	0.01	20	2.0382
2.0394	0.01	30	1.9987
2.3388	0.01	40	1.9706
3.0378	0.02	50	1.9866
1.511	0.02	60	1.9453
1.6499	0.02	70	1.9309
1.9693	0.03	80	1.9168
2.2389	0.03	90	1.9169
2.7812	0.03	100	1.9367
1.542	0.04	110	1.9202
1.574	0.04	120	1.9088
1.9916	0.04	130	1.8989
2.081	0.05	140	1.8862
2.768	0.05	150	1.9108
1.4699	0.05	160	1.8984
1.5366	0.06	170	1.8877
2.0133	0.06	180	1.8812
2.2186	0.06	190	1.8795
2.7003	0.07	200	1.8882
1.5169	0.07	210	1.8720
1.5444	0.07	220	1.8801
1.726	0.08	230	1.8732
2.0348	0.08	240	1.8657
2.6121	0.09	250	1.8702
1.5258	0.09	260	1.8655
1.5423	0.09	270	1.8733
1.8095	0.1	280	1.8505
2.0462	0.1	290	1.8455
2.5442	0.1	300	1.8552
1.4565	0.11	310	1.8586
1.4278	0.11	320	1.8491
1.7626	0.11	330	1.8358
1.9469	0.12	340	1.8427
2.5378	0.12	350	1.8580
1.4248	0.12	360	1.8499
1.586	0.13	370	1.8378
1.9637	0.13	380	1.8311
1.9733	0.13	390	1.8352
2.6789	0.14	400	1.8543
1.4521	0.14	410	1.8411
1.4683	0.14	420	1.8428
1.862	0.15	430	1.8331
2.0159	0.15	440	1.8304
2.5851	0.15	450	1.8385
1.4911	0.16	460	1.8309
1.5463	0.16	470	1.8262
1.8454	0.16	480	1.8137
2.0086	0.17	490	1.8143
2.6965	0.17	500	1.8230

Framework versions

PEFT 0.10.0
Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

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