vit-convnext-mistral-RSICD-with-4-captioning

swadhindas324/vit-convnext-mistral-RSICD-with-4-captioning

vit-convnext-mistral-RSICD-with-4-captioning is a machine learning model from swadhindas324. 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 transformers.

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

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

438M

5.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.8 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 3, 2026
Updated: Jul 3, 2026
SHA: 5cc37329

Model card

From the Hugging Face model README

vit-convnext-mistral-RSICD-with-4-captioning

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

Loss: 0.8467
Accuracy: 82.1
Bleu-1: 0.6247
Bleu-2: 0.4908
Bleu-3: 0.3998
Bleu-4: 0.3338
Meteor: 0.5847
Rouge-l: 0.5517
Cider: 1.7829

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: 64
eval_batch_size: 64
seed: 50
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 128
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
No log	1.0	768	0.6890	80.35	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9594	2.0	1536	0.6625	79.36	0.5526	0.3974	0.2971	0.2283	0.5217	0.4777	0.8622
0.4742	3.0	2304	0.6209	81.52	0.6991	0.5725	0.4764	0.3995	0.6706	0.6299	2.1187
0.3613	4.0	3072	0.6634	81.89	0.6720	0.5444	0.4509	0.3789	0.6528	0.6120	2.0542
0.3613	5.0	3840	0.7246	81.59	0.6644	0.5353	0.4442	0.3757	0.6264	0.5894	2.0102
0.2498	6.0	4608	0.7661	82.47	0.6747	0.5487	0.4587	0.3906	0.6250	0.5983	2.0941
0.1933	7.0	5376	0.8274	82.02	0.6448	0.5131	0.4190	0.3495	0.6190	0.5715	1.8927
0.1676	8.0	6144	0.8467	82.1	0.6247	0.4908	0.3998	0.3338	0.5847	0.5517	1.7829

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

Library: transformers
Type: vision-encoder-decoder
Created: Jul 3, 2026
Updated: Jul 3, 2026