vit-convnext-Mistral-NWPU-without-captioning

swadhindas324/vit-convnext-Mistral-NWPU-without-captioning

vit-convnext-Mistral-NWPU-without-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

246

Public

Parameters

438M

10.5 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 15, 2026
Updated: Jul 16, 2026
SHA: c9fc9e52

Model card

From the Hugging Face model README

vit-convnext-Mistral-NWPU-without-captioning

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

Loss: 0.7152
Accuracy: 86.03
Bleu-1: 0.8517
Bleu-2: 0.7622
Bleu-3: 0.6907
Bleu-4: 0.6330
Meteor: 0.7662
Rouge-l: 0.7519
Cider: 1.7528

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
0.9127	1.0	2215	0.8663	84.26	0.5414	0.3751	0.2608	0.1740	0.4277	0.3931	0.1700
0.7081	2.0	4430	0.6573	84.62	0.8206	0.7151	0.6330	0.5670	0.7187	0.7053	1.6150
0.6160	3.0	6645	0.6176	84.8	0.8263	0.7277	0.6492	0.5855	0.7464	0.7308	1.6939
0.5695	4.0	8860	0.6049	85.46	0.8577	0.7720	0.7011	0.6421	0.7690	0.7568	1.7658
0.5364	5.0	11075	0.5992	85.63	0.8632	0.7759	0.7052	0.6471	0.7728	0.7618	1.7980
0.5072	6.0	13290	0.6026	85.68	0.8553	0.7660	0.6928	0.6334	0.7791	0.7609	1.8060
0.4967	7.0	15505	0.6187	85.97	0.8545	0.7670	0.6964	0.6395	0.7801	0.7610	1.8101
0.4750	8.0	17720	0.6298	86.11	0.8568	0.7704	0.7001	0.6427	0.7700	0.7606	1.8042
0.4537	9.0	19935	0.6371	86.13	0.8605	0.7733	0.6996	0.6389	0.7820	0.7661	1.7836
0.4354	10.0	22150	0.6564	86.12	0.8562	0.7689	0.6975	0.6394	0.7688	0.7584	1.8225
0.4173	11.0	24365	0.6674	86.18	0.8603	0.7720	0.7007	0.6427	0.7809	0.7659	1.8056
0.4004	12.0	26580	0.6882	86.1	0.8540	0.7644	0.6927	0.6352	0.7646	0.7543	1.7460
0.4135	13.0	28795	0.6968	86.07	0.8491	0.7593	0.6863	0.6274	0.7662	0.7503	1.7297
0.3942	14.0	31010	0.7152	86.03	0.8517	0.7622	0.6907	0.6330	0.7662	0.7519	1.7528

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 15, 2026
Updated: Jul 16, 2026