vit-convnext-mistral-RSICD-with-8-captioning

swadhindas324/vit-convnext-mistral-RSICD-with-8-captioning

vit-convnext-mistral-RSICD-with-8-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

1% of all-time downloads

All-time downloads

150

Public

Parameters

438M

7 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: 0e125bf1

Model card

From the Hugging Face model README

vit-convnext-mistral-RSICD-with-8-captioning

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

Loss: 0.8669
Accuracy: 84.07
Bleu-1: 0.7351
Bleu-2: 0.6142
Bleu-3: 0.5215
Bleu-4: 0.4484
Meteor: 0.6824
Rouge-l: 0.6570
Cider: 2.4471

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	0.6912	80.57	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9613	2.0	1536	0.6663	79.37	0.5464	0.3887	0.2887	0.2200	0.5130	0.4734	0.8232
0.4779	3.0	2304	0.6232	81.88	0.7214	0.5989	0.5046	0.4283	0.6926	0.6535	2.3241
0.3613	4.0	3072	0.6633	83.51	0.7402	0.6241	0.5362	0.4659	0.6866	0.6580	2.4857
0.3613	5.0	3840	0.7131	83.31	0.7463	0.6302	0.5404	0.4695	0.6798	0.6607	2.5527
0.2524	6.0	4608	0.7585	83.96	0.7372	0.6196	0.5313	0.4614	0.6765	0.6545	2.5128
0.1982	7.0	5376	0.8154	83.36	0.7196	0.6021	0.5108	0.4372	0.6961	0.6535	2.4308
0.1730	8.0	6144	0.8187	83.59	0.7168	0.5951	0.5018	0.4298	0.6827	0.6424	2.3597
0.1730	9.0	6912	0.8533	83.89	0.7335	0.6127	0.5216	0.4487	0.6775	0.6531	2.4155
0.1532	10.0	7680	0.8669	84.07	0.7351	0.6142	0.5215	0.4484	0.6824	0.6570	2.4471

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