Vigogne70b-fans

affecto/Vigogne70b-fans

Vigogne70b-fans is a machine learning model from affecto. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Nov 24, 2023

Repo size

3.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors131 MB · 100%

At a glance

License: llama2
Access: Public
Created: Nov 24, 2023
Updated: Nov 24, 2023
SHA: 49128d8e

Base models

TheBloke/vigogne-2-70B-chat-GPTQ

Model card

From the Hugging Face model README

Vigogne70b-fans

This model is a fine-tuned version of TheBloke/vigogne-2-70B-chat-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9593

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: 0.0004
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
training_steps: 200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.9503	0.02	10	1.6354
1.2959	0.04	20	1.2117
1.2316	0.07	30	1.1256
1.1742	0.09	40	1.0960
1.1643	0.11	50	1.0677
1.0667	0.13	60	1.0449
1.0232	0.15	70	1.0391
0.9864	0.17	80	1.0272
1.0588	0.2	90	1.0206
0.906	0.22	100	1.0020
1.098	0.24	110	0.9979
0.9973	0.26	120	0.9883
0.9999	0.28	130	1.0002
1.121	0.31	140	0.9752
0.9726	0.33	150	0.9722
1.015	0.35	160	0.9680
0.8247	0.37	170	0.9664
0.823	0.39	180	0.9613
0.8921	0.41	190	0.9607
1.0024	0.44	200	0.9593

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

License: llama2
Created: Nov 24, 2023
Updated: Nov 24, 2023