vit-resnet-mistral-NWPU-with-7-captioning

swadhindas324/vit-resnet-mistral-NWPU-with-7-captioning

vit-resnet-mistral-NWPU-with-7-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

3% of all-time downloads

All-time downloads

139

Public

Parameters

301M

8.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 5, 2026
Updated: Jul 5, 2026
SHA: 9480529f

Model card

From the Hugging Face model README

vit-resnet-mistral-NWPU-with-7-captioning

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

Loss: 0.3639
Accuracy: 86.29
Bleu-1: 0.8596
Bleu-2: 0.7713
Bleu-3: 0.6995
Bleu-4: 0.6409
Meteor: 0.7597
Rouge-l: 0.7542
Cider: 1.7632

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
0.5079	1.0	2215	0.4756	82.99	0.5062	0.3499	0.2396	0.1568	0.4183	0.3744	0.1308
0.4044	2.0	4430	0.3607	84.9	0.8150	0.7062	0.6219	0.5546	0.7145	0.6993	1.5802
0.3306	3.0	6645	0.3248	85.09	0.8278	0.7298	0.6519	0.5888	0.7408	0.7296	1.6979
0.2994	4.0	8860	0.3135	85.57	0.8583	0.7733	0.7018	0.6424	0.7701	0.7573	1.7737
0.2812	5.0	11075	0.3097	85.76	0.8678	0.7822	0.7128	0.6560	0.7736	0.7652	1.8122
0.2659	6.0	13290	0.3106	85.64	0.8562	0.7682	0.6967	0.6383	0.7781	0.7620	1.8217
0.2596	7.0	15505	0.3154	86.19	0.8602	0.7745	0.7060	0.6503	0.7768	0.7632	1.8264
0.2488	8.0	17720	0.3207	86.16	0.8655	0.7822	0.7135	0.6575	0.7791	0.7689	1.8329
0.2384	9.0	19935	0.3241	86.13	0.8677	0.7831	0.7117	0.6528	0.7855	0.7736	1.8159
0.2285	10.0	22150	0.3306	86.03	0.8594	0.7749	0.7056	0.6488	0.7754	0.7660	1.8252
0.2187	11.0	24365	0.3379	86.21	0.8648	0.7787	0.7084	0.6510	0.7817	0.7680	1.8212
0.2090	12.0	26580	0.3485	86.25	0.8608	0.7730	0.7014	0.6438	0.7705	0.7618	1.7850
0.2150	13.0	28795	0.3529	86.3	0.8582	0.7702	0.6975	0.6379	0.7674	0.7544	1.7825
0.2034	14.0	31010	0.3639	86.29	0.8596	0.7713	0.6995	0.6409	0.7597	0.7542	1.7632

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 5, 2026
Updated: Jul 5, 2026