gm-qlora-float16-idefics2-8b-midefics-1only

gimarchetti/gm-qlora-float16-idefics2-8b-midefics-1only

gm-qlora-float16-idefics2-8b-midefics-1only is a machine learning model from gimarchetti. 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 apache-2.0.

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

Downloads · 30 days

Access

Public

Updated May 12, 2024

Repo size

93.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors93.4 MB · 100%

At a glance

License: apache-2.0
Access: Public
Created: May 12, 2024
Updated: May 12, 2024
SHA: 517513ab

Base models

HuggingFaceM4/idefics2-8b

Model card

From the Hugging Face model README

gm-qlora-float16-idefics2-8b-midefics-1only

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6549

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: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 10
total_train_batch_size: 20
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.6097	0.2	38	0.7500
0.7887	0.4	76	0.7131
0.8106	0.6	114	0.6939
0.7538	0.8	152	0.6715
0.7429	1.0	190	0.6614
0.5333	1.2	228	0.6809
0.5278	1.4	266	0.6734
0.527	1.6	304	0.6639
0.5228	1.8	342	0.6578
0.5038	2.0	380	0.6549

Framework versions

Transformers 4.41.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.19.1
Tokenizers 0.19.1

License: apache-2.0
Created: May 12, 2024
Updated: May 12, 2024